Best Incremental Learning
Incremental Learning Repository: A collection of documents, papers, source code, and talks for incremental learning.
Keywords: Incremental Learning, Continual Learning, Continuous Learning, Lifelong Learning, Catastrophic Forgetting
CATALOGUE
Quick Start ✨ Survey ✨ Papers by Categories ✨ Datasets ✨ Tutorial, Workshop, & Talks
1 Quick Start
Continual Learning | Papers With Code
Incremental Learning | Papers With Code
Class Incremental Learning from the Past to Present by 思悥 | 知乎 (In Chinese)
A Little Survey of Incremental Learning | 知乎 (In Chinese)
Origin of the Study
-
Catastrophic Forgetting, Rehearsal and Pseudorehearsal(2001)[paper]
-
Catastrophic forgetting in connectionist networks(1999)[paper]
-
Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem(1989)[paper]
Toolbox & Framework
-
[FACIL] Class-incremental learning: survey and performance evaluation on image classification(TPAMI 2022)[paper][code]
-
[Avalanche] Avalanche: An End-to-End Library for Continual Learning(CVPR 2021)[paper][code]
-
[PyCIL] PyCIL: A Python Toolbox for Class-Incremental Learning(arXiv 2021)[paper][code]
-
[Mammoth] An Extendible (General) Continual Learning Framework for Pytorch [code]
-
[PyContinual] An Easy and Extendible Framework for Continual Learning[code]
Books
- Lifelong Machine Learning [Link]
2 Survey
2.1 Surveys
-
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning(arXiv 2023)[github]
-
Deep Class-Incremental Learning: A Survey(arXiv 2023)[paper][code]
-
A Comprehensive Survey of Continual Learning: Theory, Method and Application(arxiv 2023)[paper]
-
[FACIL] Class-incremental learning: survey and performance evaluation on image classification(TPAMI 2022)[paper][code]
-
Online Continual Learning in Image Classification: An Empirical Survey (Neurocomputing 2021)[paper]
-
A continual learning survey: Defying forgetting in classification tasks (TPAMI 2021) [paper]
-
Rehearsal revealed: The limits and merits of revisiting samples in continual learning (ICCV 2021)[paper]
-
Continual Lifelong Learning in Natural Language Processing: A Survey (COLING 2020) [paper]
-
A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (Neural Networks 2020) [paper]
-
Embracing Change: Continual Learning in Deep Neural Networks(Trends in Cognitive Sciences 2020)[paper]
-
Towards Continual Reinforcement Learning: A Review and Perspectives(arXiv 2020)[paper]
-
Class-incremental learning: survey and performance evaluation(arXiv 2020) [paper]
-
A comprehensive, application-oriented study of catastrophic forgetting in DNNs (ICLR 2019) [paper]
-
Three scenarios for continual learning (arXiv 2019) [paper]
-
Continual lifelong learning with neural networks: A review(arXiv 2019)[paper]
-
类别增量学习研究进展和性能评价 (自动化学报 2023)[paper]
2.2 Analysis & Study
-
How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning?(NeurIPS 2022)[paper]
-
[WPTP] A Theoretical Study on Solving Continual Learning(NeurIPS 2022)[paper][code]
-
The Challenges of Continuous Self-Supervised Learning(ECCV 2022)[peper]
-
Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions(NeurIPS 2022)[paper]
-
A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal(NeurIPS 2022)[paper][code]
-
Exploring Example Influence in Continual Learning(NeurIPS 2022)[paper]
-
Biological underpinnings for lifelong learning machines(Nat. Mach. Intell. 2022)[paper]
-
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning(CVPR 2022)[paper][code]
-
[OpenLORIS-Object] Towards Lifelong Object Recognition: A Dataset and Benchmark(Pattern Recognit 2022)[paper]
-
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning (CVPR 2022) [paper]
-
Learngene: From Open-World to Your Learning Task (AAAI 2022) [paper]
-
Continual Normalization: Rethinking Batch Normalization for Online Continual Learning (ICLR 2022) [paper]
-
[CLEVA-Compass] CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability (ICLR 2022) [paper][code]
-
Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting (ICLR 2022) [paper]
-
[CKL] Towards Continual Knowledge Learning of Language Models (ICLR 2022) [paper]
-
Pretrained Language Model in Continual Learning: A Comparative Study (ICLR 2022) [paper]
-
Effect of scale on catastrophic forgetting in neural networks (ICLR 2022) [paper]
-
LifeLonger: A Benchmark for Continual Disease Classification(arXiv 2022)[paper]
-
[CDDB] A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials(arXiv 2022)[paper]
-
[BN Tricks] Diagnosing Batch Normalization in Class Incremental Learning(arXiv 2022)[paper]
-
Architecture Matters in Continual Learning(arXiv 2022)[paper]
-
Learning where to learn: Gradient sparsity in meta and continual learning(NeurIPS 2021) [paper]
-
Continuous Coordination As a Realistic Scenario for Lifelong Learning(ICML 2021)[paper]
-
Understanding the Role of Training Regimes in Continual Learning (NeurIPS 2020)[paper]
-
Optimal Continual Learning has Perfect Memory and is NP-HARD (ICML 2020)[paper]
2.3 Settings
-
[FSCIL] Few-shot Class Incremental Learning [Link]
-
[DCIL] Decentralized Class Incremental Learning [paper][Setting]
3 Papers by Categories
Tips: you can use ctrl+F to match abbreviations with articles, or browse the paper list below.
3.1 From an Algorithm Perspective
Network Structure | Rehearsal | |
---|---|---|
2023 | A-Prompts (arXiv 2023)[paper] ESN(AAAI 2023)[paper][code] RevisitingCIL(arXiv 2023)[paper][code] LwP(ICLR 2023)[paper] SDMLP(ICLR 2023)[paper] SaLinA(ICLR 2023)[paper][code] BEEF(ICLR 2023)[paper][code] WaRP(ICLR 2023)[paper] OBC(ICLR 2023)[paper] NC-FSCIL(ICLR 2023)[paper][code] iVoro(ICLR 2023)[paper] DAS(ICLR 2023)[paper] Progressive Prompts(ICLR 2023)[paper] SDP(ICLR 2023)[paper][code] iLDR(ICLR 2023)[paper] SoftNet-FSCIL(ICLR 2023)[paper][code] PAR(CVPR 2023)[paper] PETAL(CVPR 2023)[paper][code] SAVC(CVPR 2023)[paper][code] CODA-Prompt(CVPR 2023)[paper][code] |
FeTrIL(WACV 2023)[paper][code] ESMER(ICLR 2023)[paper][code] MEMO(ICLR 2023)[paper][code] CUDOS(ICLR 2023)[paper] ACGAN(ICLR 2023)[paper][code] TAMiL(ICLR 2023)[paper][code] RSOI(CVPR 2023)[paper][code] TBBN(CVPR 2023)[paper] AMSS(CVPR 2023)[paper] DGCL(CVPR 2023)[paper] PCR(CVPR 2023)[paper][code] FMWISS(CVPR 2023)[paper] CL-DETR(CVPR 2023)[paper][code] PIVOT(CVPR 2023)[paper] CIM-CIL(CVPR 2023)[paper][code] DNE(CVPR 2023)[paper] |
2022 | RD-IOD(ACM Trans 2022)[paper] NCM(arXiv 2022)[paper] IPP(arXiv 2022)[paper] Incremental-DETR(arXiv 2022)[paper] ELI(CVPR 2022)[paper] CASSLE(CVPR 2022)[paper][code] iFS-RCNN(CVPR 2022)[paper] WILSON(CVPR 2022)[paper][code] Connector(CVPR 2022)[paper][code] PAD(CVPR 2022)[paper] ERD(CVPR 2022)[paper][code] AFC(CVPR 2022)[paper][code] FACT(CVPR 2022)[paper][code] L2P(CVPR 2022)[paper][code] MEAT(CVPR 2022)[paper][code] RCIL(CVPR 2022)[paper][code] ZITS(CVPR 2022)[paper][code] MTPSL(CVPR 2022)[paper][code] MMA(CVPR-Workshop 2022)[paper] CoSCL(ECCV 2022)[paper][code] AdNS(ECCV 2022)[paper] ProCA(ECCV 2022)[paper][code] R-DFCIL(ECCV 2022)[paper][code] S3C(ECCV 2022)[paper][code] H^2^(ECCV 2022)[paper] DualPrompt(ECCV 2022)[paper] ALICE(ECCV 2022)[paper][code] RU-TIL(ECCV 2022)[paper][code] FOSTER(ECCV 2022)[paper] SSR(ICLR 2022)[paper][code] RGO(ICLR 2022)[paper] TRGP(ICLR 2022)[paper] AGCN(ICME 2022)[paper][code] WSN(ICML 2022)[paper][code] NISPA(ICML 2022)[paper][code] S-FSVI(ICML 2022)[paper][code] CUBER(NeurIPS 2022)[paper] ADA(NeurIPS 2022)[paper] CLOM(NeurIPS 2022)[paper] S-Prompt(NeurIPS 2022)[paper] ALIFE(NIPS 2022)[paper] PMT(NIPS 2022)[paper] STCISS(TNNLS 2022)[paper] DSN(TPAMI 2022)[paper] MgSvF(TPAMI 2022)[paper] TransIL(WACV 2022)[paper] |
NER-FSCIL(ACL 2022)[paper] LIMIT(arXiv 2022)[paper] EMP(arXiv 2022)[paper] SPTM(CVPR 2022)[paper] BER(CVPR 2022)[paper] Sylph(CVPR 2022)[paper] MetaFSCIL(CVPR 2022)[paper] FCIL(CVPR 2022)[paper][code] FILIT(CVPR 2022)[paper] PuriDivER(CVPR 2022)[paper][code] SNCL(CVPR 2022)[paper] DVC(CVPR 2022)[paper][code] CVS(CVPR 2022)[paper] CPL(CVPR 2022)[paper] GCR(CVPR 2022)[paper] LVT(CVPR 2022)[paper] vCLIMB(CVPR 2022)[paper][code] Learn-to-Imagine(CVPR 2022)[paper][code] DCR(CVPR 2022)[paper] DIY-FSCIL(CVPR 2022)[paper] C-FSCIL(CVPR 2022)[paper][code] SSRE(CVPR 2022)[paper] CwD(CVPR 2022)[paper][code] MSL(CVPR 2022)[paper] DyTox(CVPR 2022)[paper][code] X-DER(ECCV 2022)[paper] clsss-iNCD(ECCV 2022)[paper][code] ARI(ECCV 2022)[paper][code] Long-Tailed-CIL(ECCV 2022)[paper][code] LIRF(ECCV 2022)[paper] DSDM(ECCV 2022)[paper][code] CVT(ECCV 2022)[paper] TwF(ECCV 2022)[paper][code] CSCCT(ECCV 2022)[paper][code] DLCFT(ECCV 2022)[paper] ERDR(ECCV2022)[paper] NCDwF(ECCV2022)[paper] CoMPS(ICLR 2022)[paper] i-fuzzy(ICLR 2022)[paper][code] CLS-ER(ICLR 2022)[paper][code] MRDC(ICLR 2022)[paper][code] OCS(ICLR 2022)[paper] InfoRS(ICLR 2022)[paper] ER-AML(ICLR 2022)[paper][code] FAS(ICLR 2022)[paper] LUMP(ICLR 2022)[paper] CF-IL(ICLR 2022)[paper][code] LFPT5(ICLR 2022)[paper][code] Model Zoo(ICLR 2022)[paper] OCM(ICML 2022)[paper][code] DRO(ICML 2022)[paper][code] EAK(ICPR 2022)[paper] RAR(NeurIPS 2022)[paper] LiDER(NeurIPS 2022)[paper] SparCL(NeurIPS 2022)[paper] ClonEx-SAC(NeurIPS 2022)[paper] ODDL(NeurIPS 2022)[paper] CSSL(PRL 2022)[paper] MBP(TNNLS 2022)[paper] CandVot(WACV 2022)[paper] FlashCards(WACV 2022)[paper] |
2021 | Meta-DR(CVPR 2021)[paper] continual cross-modal retrieval(CVPR 2021)[paper] DER(CVPR 2021)[paper][code] EFT(CVPR 2021)[paper][code] PASS(CVPR 2021)[paper][code] GeoDL(CVPR 2021)[paper][code] IL-ReduNet(CVPR 2021)[paper] PIGWM(CVPR 2021)[paper] BLIP(CVPR 2021)[paper][code] Adam-NSCL(CVPR 2021)[paper][code] PLOP(CVPR 2021)[paper][code] SDR(CVPR 2021)[paper][code] SKD(CVPR 2021)[paper] Always Be Dreaming(ICCV 2021)[paper][code] SPB(ICCV 2021)[paper] Else-Net(ICCV 2021)[paper] LCwoF-Framework(ICCV 2021)[paper] AFEC(NeurIPS 2021)[paper][code] F2M(NeurIPS 2021)[paper][code] NCL(NeurIPS 2021)[paper][code] BCL(NeurIPS 2021)[paper][code] Posterior Meta-Replay(NeurIPS 2021)[paper] MARK(NeurIPS 2021)[paper][code] Co-occur(NeurIPS 2021)[paper][code] LINC(AAAI 2021)[paper] CLNER(AAAI 2021)[paper] CLIS(AAAI 2021)[paper] PCL(AAAI 2021)[paper] MAS3(AAAI 2021)[paper] FSLL(AAAI 2021)[paper] VAR-GPs(ICML 2021)[paper] BSA(ICML 2021)[paper] GPM(ICLR 2021)[paper][code] |
TMN(TNNLS 2021)[paper] RKD(AAAI 2021)[paper] AANets(CVPR 2021)[paper][code] ORDisCo(CVPR 2021)[paper] DDE(CVPR 2021)[paper][code] IIRC(CVPR 2021)[paper] Hyper-LifelongGAN(CVPR 2021)[paper] CEC(CVPR 2021)[paper] iMTFA(CVPR 2021)[paper] RM(CVPR 2021)[paper] LOGD(CVPR 2021)[paper] SPPR(CVPR 2021)[paper] LReID(CVPR 2021)[paper][code] SS-IL(ICCV 2021)[paper] TCD(ICCV 2021)[paper] CLOC(ICCV 2021)[paper][code] CoPE(ICCV 2021)[paper][code] Co2L(ICCV 2021)[paper][code] SPR(ICCV 2021)[paper] NACL(ICCV 2021)[paper] CL-HSCNet(ICCV 2021)[paper][code] RECALL(ICCV 2021)[paper][code] VAE(ICCV 2021)[paper] ERT(ICPR 2021)[paper][code] KCL(ICML 2021)[paper][code] MLIOD(TPAMI 2021)[paper][code] BNS(NeurIPS 2021)[paper] FS-DGPM(NeurIPS 2021)[paper] SSUL(NeurIPS 2021)[paper] DualNet(NeurIPS 2021)[paper] classAug(NeurIPS 2021)[paper] GMED(NeurIPS 2021)[paper] BooVAE(NeurIPS 2021)[paper][code] GeMCL(NeurIPS 2021)[paper] RMM(NIPS 2021)[paper][code] LSF(IJCAI 2021)[paper] ASER(AAAI 2021)[paper][code] CML(AAAI 2021)[paper][code] HAL(AAAI 2021)[paper] MDMT(AAAI 2021)[paper] AU(WACV 2021)[paper] IDBR(NAACL 2021)[paper][code] COIL(ACM MM 2021)[paper] |
2020 | CWR*(CVPR 2020)[paper] MiB(CVPR 2020)[paper][code] K-FAC(CVPR 2020)[paper] SDC(CVPR 2020)[paper][code] NLTF(AAAI 2020) [paper] CLCL(ICLR 2020)[paper][code] APD(ICLR 2020)[paper] HYPERCL(ICLR 2020)[paper][code] CN-DPM(ICLR 2020)[paper] UCB(ICLR 2020)[paper][code] CLAW(ICLR 2020)[paper] CAT(NeurIPS 2020)[paper][code] AGS-CL(NeurIPS 2020)[paper] MERLIN(NeurIPS 2020)[paper][code] OSAKA(NeurIPS 2020)[paper][code] RATT(NeurIPS 2020)[paper] CCLL(NeurIPS 2020)[paper] CIDA(ECCV 2020)[paper] GraphSAIL(CIKM 2020)[paper] ANML(ECAI 2020)[paper][code] ICWR(BMVC 2020)[paper] DAM(TPAMI 2020)[paper] OGD(PMLR 2020)[paper] MC-OCL(ECCV2020)[paper][code] RCM(ECCV 2020)[paper][code] OvA-INN(IJCNN 2020)[paper] XtarNet(ICLM 2020)[paper][code] DMC(WACV 2020)[paper] |
iTAML(CVPR 2020)[paper][code] FSCIL(CVPR 2020)[paper][code] GFR(CVPR 2020)[paper][code] OSIL(CVPR 2020)[paper] ONCE(CVPR 2020)[paper] WA(CVPR 2020)[paper][code] CGATE(CVPR 2020)[paper][code] Mnemonics Training(CVPR 2020)[paper][code] MEGA(NeurIPS 2020)[paper] GAN Memory(NeurIPS 2020)[paper][code] Coreset(NeurIPS 2020)[paper] FROMP(NeurIPS 2020)[paper][code] DER(NeurIPS 2020)[paper][code] InstAParam(NeurIPS 2020)[paper] BOCL(AAAI 2020)[paper] REMIND(ECCV 2020)[paper][code] ACL(ECCV 2020)[paper][code] TPCIL(ECCV 2020)[paper] GDumb(ECCV 2020)[paper][code] PRS(ECCV 2020)[paper] PODNet(ECCV 2020)[paper][code] FA(ECCV 2020)[paper] L-VAEGAN(ECCV 2020)[paper] Piggyback GAN(ECCV 2020)[paper][code] IDA(ECCV 2020)[paper] RCM(ECCV 2020)[paper] LAMOL(ICLR 2020)[paper][code] FRCL(ICLR 2020)[paper][code] GRS(ICLR 2020)[paper] Brain-inspired replay(Natrue Communications 2020)[paper][code] CLIFER(FG 2020)[paper] ScaIL(WACV 2020)[paper][code] ARPER(EMNLP 2020)[paper] DnR(COLING 2020)[paper] ADER(RecSys 2020)[paper][code] MUC(ECCV 2020)[paper][code] |
2019 | LwM(CVPR 2019)[paper] CPG(NeurIPS 2019)[paper][code] UCL(NeurIPS 2019)[paper] OML(NeurIPS 2019)[paper][code] ALASSO(ICCV 2019)[paper] Learn-to-Grow(PMLR 2019)[paper] OWM(Nature Machine Intelligence 2019)[paper][code] |
LUCIR(CVPR 2019)[paper][code] TFCL(CVPR 2019)[paper] GD(CVPR 2019)[paper][code] DGM(CVPR 2019)[paper] BiC(CVPR 2019)[paper][code] MER(ICLR 2019)[paper][code] PGMA(ICLR 2019)[paper] A-GEM(ICLR 2019)[paper][code] IL2M(ICCV 2019)[paper] ILCAN(ICCV 2019)[paper] Lifelong GAN(ICCV 2019)[paper] GSS(NIPS 2019)[paper] ER(NIPS 2019)[paper] MIR(NIPS 2019)[paper][code] RPS-Net(NIPS 2019)[paper] CLEER(IJCAI 2019)[paper] PAE(ICMR 2019)[paper][code] |
2018 | PackNet(CVPR 2018)[paper][code] OLA(NIPS 2018)[paper] RCL(NIPS 2018)[paper][code] MARL(ICLR 2018)[paper] DEN(ICLR 2018)[paper][code] P&C(ICML 2018)[paper] Piggyback(ECCV 2018)[paper][code] RWalk(ECCV 2018)[paper] MAS(ECCV 2018)[paper][code] R-EWC(ICPR 2018)[paper][code] HAT(PMLR 2018)[paper][code] |
MeRGANs(NIPS 2018)[paper][code] EEIL(ECCV 2018)[paper][code] Adaptation by Distillation(ECCV 2018)[paper] ESGR(BMVC 2018)[paper][code] VCL(ICLR 2018)[paper] FearNet(ICLR 2018)[paper] DGDMN(ICLR 2018)[paper] |
2017 | Expert Gate(CVPR 2017)[paper][code] ILOD(ICCV 2017)[paper][code] EBLL(ICCV2017)[paper] IMM(NIPS 2017)[paper][code] SI(ICML 2017)[paper][code] EWC(PNAS 2017)[paper][code] |
iCARL(CVPR 2017)[paper][code] GEM(NIPS 2017)[paper][code] DGR(NIPS 2017)[paper][code] |
2016 | LwF(ECCV 2016)[paper][code] |
3.2 From a Data Deployment Perspective
Data decentralized incremental learning
- [DCID] Deep Class Incremental Learning from Decentralized Data(TNNLS 2022)[paper][code]
- [GLFC] Federated Class-Incremental Learning(CVPR 2022)[paper][code]
- [FedWeIT] Federated Continual Learning with Weighted Inter-client Transfer(ICML 2021)[paper][code]
Data centralized incremental learning
All other studies aforementioned except those already in the 'Decentralized' section.
4 Datasets
datasets | describes |
---|---|
ImageNet | There are 1.28 million training images and 50,000 validation images in over 1,000 categories. Usually crop into 224×224 color image |
TinyImageNet | Contains 100,000 64×64 color images of 200 categories (500 per category). Each class has 500 training images, 50 validation images, and 50 test images. |
MiniImageNet | This dataset is a subset of ImageNet used for few-shot learning. It consists of 60, 000 colour images of size 84 × 84 with 100 classes, each having 600 examples. |
SubImageNet | This dataset is a 100-class subset of ImageNet's random sample, which contains approximately 130,000 images for training and 5,000 images for testing. |
CIFAR-10/100 | Both datasets contain 60,000 natural RGB images of the size 32 × 32, including 50,000 training and 10,000 test images. CIFAR10 has 10 classes, while CIFAR100 has 100 classes. |
CORe50 | This dataset consists of 164,866 128×128 RGB-D images: 11 sessions × 50 objects × (around 300) frames per session. Github CORe50: a New Dataset and Benchmark for Continuous Object Recognition |
OpenLORIS-Object | This is the first real-world dataset for robotic vision with independent and quantifiable environmental factors, compared with other lifelong learning datasets, with 186 instances, 63 categories and 2,138,050 images. |
5 Lecture, Tutorial, Workshop, & Talks
Life-Long learning | 李宏毅
Life-long Learning: [ppt] [pdf]
Catastrophic Forgetting [Chinese] [English]
Mitigating Catastrophic Forgetting [Chinese] [English]
Meta Learning : Learn to Learn [Chinese]
Continual AI Lecture
Open World Lifelong Learning | A Continual Machine Learning Course
Prompting-based Continual Learning | Continual AI
VALSE Webinar (In Chinese)
20211215【学无止境:深度连续学习】洪晓鹏:记忆拓扑保持的深度增量学习方法
20211215【学无止境:深度连续学习】李玺:基于深度神经网络的持续性学习理论与方法
ACM MULTIMEDIA
ACM2021 Few-shot Learning for Multi-Modality Tasks
CVPR Workshop
CVPR 2022 Workshop on Continual Learning in Computer Vision
CVPR2021 Workshop on Continual Learning in Computer Vision
CVPR2020 Workshop on Continual Learning in Computer Vision
CVPR2017 Continuous and Open-Set Learning Workshop
ICML Tutorial/Workshop
ICML 2021 Workshop on Theory and Foundation of Continual Learning
ICML 2021 Tutorial on Continual Learning with Deep Architectures
ICML2020 Workshop on Continual Learning
NeurIPS Workshop
NeurIPS2021 4th Robot Learning Workshop: Self-Supervised and Lifelong Learning
NeurIPS2018 Continual learning Workshop
NeurIPS2016 Continual Learning and Deep Networks Workshop
IJCAI Workshop
IJCAI 2021 International Workshop on Continual Semi-Supervised Learning
ContinualAI wiki
A Non-profit Research Organization and Open Community on Continual Learning for AI
CoLLAs
Conference on Lifelong Learning Agents - CoLLAs 2022
6 Competitions
achieved
3rd CLVISION CVPR Workshop Challenge 2022
IJCAI 2021 - International Workshop on Continual Semi-Supervised Learning
2rd CLVISION CVPR Workshop Challenge 2021
1rd CLVISION CVPR Workshop Challenge 2020
7 Awesome Reference
[1] https://github.com/xialeiliu/Awesome-Incremental-Learning
8 Contact Us
Should there be any concerns on this page, please don't hesitate to let us know via hongxiaopeng@ieee.org or xl330@126.com.
Full Paper List
2023
-
Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning(ICCV 2023)[paper]
-
Prototype Reminiscence and Augmented Asymmetric Knowledge Aggregation for Non-Exemplar Class-Incremental Learning(ICCV 2023)[paper]
-
When Prompt-based Incremental Learning Does Not Meet Strong Pretraining(ICCV 2023)[paper]
-
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision(ICCV 2023)[paper]
-
Dynamic Residual Classifier for Class Incremental Learning(ICCV 2023)[paper]
-
Audio-Visual Class-Incremental Learning(ICCV 2023)[paper]
-
First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning(ICCV 2023)[paper]
-
Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning(ICCV 2023)[paper]
-
Heterogeneous Forgetting Compensation for Class-Incremental Learning(ICCV 2023)[paper]
-
Masked Autoencoders are Efficient Class Incremental Learners(ICCV 2023)[paper]
-
Knowledge Restore and Transfer for Multi-Label Class-Incremental Learning(ICCV 2023)[paper]
-
Space-time Prompting for Video Class-incremental Learning(ICCV 2023)[paper]
-
CLNeRF: Continual Learning Meets NeRF(ICCV 2023)[paper]
-
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?(ICCV 2023)[paper]
-
Exemplar-Free Continual Transformer with Convolutions(ICCV 2023)[paper]
-
Self-Evolved Dynamic Expansion Model for Task-Free Continual Learning(ICCV 2023)[paper]
-
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision(ICCV 2023)[paper]
-
Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning(ICCV 2023)[paper]
-
Measuring Asymmetric Gradient Discrepancy in Parallel Continual Learning(ICCV 2023)[paper]
-
Wasserstein Expansible Variational Autoencoder for Discriminative and Generative Continual Learning(ICCV 2023)[paper]
-
Data Augmented Flatness-aware Gradient Projection for Continual Learning(ICCV 2023)[paper]
-
A Unified Continual Learning Framework with General Parameter-Efficient Tuning(ICCV 2023)[paper]
-
Introducing Language Guidance in Prompt-based Continual Learning(ICCV 2023)[paper]
-
Continual Learning for Personalized Co-speech Gesture Generation(ICCV 2023)[paper]
-
Growing a Brain with Sparsity-Inducing Generation for Continual Learning(ICCV 2023)[paper]
-
Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an Emphasis on Energy Consumption and Computational Footprint(ICCV 2023)[paper]
-
Class-Incremental Grouping Network for Continual Audio-Visual Learning(ICCV 2023)[paper]
-
ICICLE: Interpretable Class Incremental Continual Learning(ICCV 2023)[paper]
-
Online Prototype Learning for Online Continual Learning(ICCV 2023)[paper]
-
NAPA-VQ: Neighborhood-Aware Prototype Augmentation with Vector Quantization for Continual Learning(ICCV 2023)[paper]
-
Few-shot Continual Infomax Learning(ICCV 2023)[paper]
-
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model(ICCV 2023)[paper]
-
Instance and Category Supervision are Alternate Learners for Continual Learning(ICCV 2023)[paper]
-
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models(ICCV 2023)[paper]
-
CLR: Channel-wise Lightweight Reprogramming for Continual Learning(ICCV 2023)[paper]
-
Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning(ICCV 2023)[paper]
-
TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation(ICCV 2023)[paper]
-
CBA: Improving Online Continual Learning via Continual Bias Adaptor(ICCV 2023)[paper]
-
Continual Zero-Shot Learning through Semantically Guided Generative Random Walks(ICCV 2023)[paper]
-
A Soft Nearest-Neighbor Framework for Continual Semi-Supervised Learning(ICCV 2023)[paper]
-
Online Continual Learning on Hierarchical Label Expansion(ICCV 2023)[paper]
-
Generating Instance-level Prompts for Rehearsal-free Continual Learning(ICCV 2023)[paper]
-
Heterogeneous Continual Learning(CVPR 2023)[paper]
-
Partial Hypernetworks for Continual Learning(CoLLAs 2023)[paper]
-
Learnability and Algorithm for Continual Learning(ICML 2023)[paper]
-
Parameter-Level Soft-Masking for Continual Learning(ICML 2023)[paper]
-
Improving Online Continual Learning Performance and Stability with Temporal Ensembles(CoLLAs 2023)[paper]
-
Exploring Continual Learning for Code Generation Models(ACL 2023)[paper]
-
[Fed-CPrompt] Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learning(FL-ICML 2023)[paper]
-
Online Continual Learning for Robust Indoor Object Recognition(ICCV 2023)[paper]
-
Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery(ICCV 2023)[paper]
-
[XLDA] XLDA: Linear Discriminant Analysis for Scaling Continual Learning to Extreme Classification at the Edge[ICML 2023][paper]
-
[CLR] CLR: Channel-wise Lightweight Reprogramming for Continual Learning(ICCV 2023)[paper]
-
[CS-VQLA] Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery(MICCAI 2023)[paper][code]
-
Online Prototype Learning for Online Continual Learning(ICCV 2023)[paper][code]
-
Cost-effective On-device Continual Learning over Memory Hierarchy with Miro(ACM MobiCom 23)[paper]
-
[CBA] CBA: Improving Online Continual Learning via Continual Bias Adaptor(ICCV 2023)[paper]
-
[A-Prompts] Remind of the Past: Incremental Learning with Analogical Prompts(arXiv 2023)[paper]
-
[ESN] Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference(AAAI 2023)[paper][code]
-
[RevisitingCIL] Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need(arXiv 2023)[paper][code]
-
[LwP] Learning without Prejudices: Continual Unbiased Learning via Benign and Malignant Forgetting(ICLR 2023)[paper]
-
[SDMLP] Sparse Distributed Memory is a Continual Learner(ICLR 2023)[paper]
-
[SaLinA] Building a Subspace of Policies for Scalable Continual Learning(ICLR 2023)[paper][code]
-
[BEEF] BEEF:Bi-Compatible Class-Incremental Learning via Energy-Based Expansion and Fusion(ICLR 2023)[paper][code]
-
[WaRP] Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning(ICLR 2023)[paper]
-
[OBC] Online Bias Correction for Task-Free Continual Learning(ICLR 2023)[paper]
-
[NC-FSCIL] Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning(ICLR 2023)[paper][code]
-
[iVoro] Progressive Voronoi Diagram Subdivision Enables Accurate Data-free Class-Incremental Learning(ICLR 2023)[paper]
-
[DAS] Continual Learning of Language Models(ICLR 2023)[paper]
-
[Progressive Prompts] Progressive Prompts: Continual Learning for Language Models without Forgetting(ICLR 2023)[paper]
-
[SDP] Online Boundary-Free Continual Learning by Scheduled Data Prior(ICLR 2023)[paper][code]
-
[iLDR] Incremental Learning of Structured Memory via Closed-Loop Transcription(ICLR 2023)[paper]
-
[SoftNet-FSCIL] On the Soft-Subnetwork for Few-Shot Class Incremental LearningOn the Soft-Subnetwork for Few-Shot Class Incremental Learning(ICLR 2023)[paper][code]
-
[ESMER] Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning(ICLR 2023)[paper][code]
-
[MEMO] A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning(ICLR 2023)[paper][code]
-
[CUDOS] Continual Unsupervised Disentangling of Self-Organizing Representations(ICLR 2023)[paper]
-
[ACGAN] Better Generative Replay for Continual Federated Learning(ICLR 2023)[paper][code]
-
[TAMiL] Task-Aware Information Routing from Common Representation Space in Lifelong Learning(ICLR 2023)[paper][code]
-
[FeTrIL] Feature Translation for Exemplar-Free Class-Incremental Learning(WACV 2023)[paper][code]
-
[RSOI] Regularizing Second-Order Influences for Continual Learning(CVPR 2023)[paper][code]
-
[TBBN] Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning(CVPR 2023)[paper]
-
[AMSS] Continual Semantic Segmentation with Automatic Memory Sample Selection(CVPR 2023)[paper]
-
[DGCL] Exploring Data Geometry for Continual Learning(CVPR 2023)[paper]
-
[PCR] PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning(CVPR 2023)[paper][code]
-
[FMWISS] Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation(CVPR 2023)[paper]
-
[CL-DETR] Continual Detection Transformer for Incremental Object Detection(CVPR 2023)[paper][code]
-
[PIVOT] PIVOT: Prompting for Video Continual Learning(CVPR 2023)[paper]
-
[CIM-CIL] Class-Incremental Exemplar Compression for Class-Incremental Learning(CVPR 2023)[paper][code]
-
[DNE] Dense Network Expansion for Class Incremental Learning(CVPR 2023)[paper]
-
[PAR] Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning(CVPR 2023)[paper]
-
[PETAL] A Probabilistic Framework for Lifelong Test-Time Adaptation(CVPR 2023)[paper][code]
-
[SAVC] Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning(CVPR 2023)[paper][code]
-
[CODA-Prompt] CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning(CVPR 2023)[paper][code]
2022
- [RD-IOD] RD-IOD: Two-Level Residual-Distillation-Based Triple-Network for Incremental Object Detection(ACM Trans 2022)[paper]
- [NCM] Exemplar-free Online Continual Learning(arXiv 2022)[paper]
- [IPP] Incremental Prototype Prompt-tuning with Pre-trained Representation for Class Incremental Learning(arXiv 2022)[paper]
- [Incremental-DETR] Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning(arXiv 2022)[paper]
- [ELI] Energy-Based Latent Aligner for Incremental Learning(CVPR 2022)[paper]
- [CASSLE] Self-Supervised Models Are Continual Learners(CVPR 2022)[paper][code]
- [iFS-RCNN] iFS-RCNN: An Incremental Few-Shot Instance Segmenter(CVPR 2022)[paper]
- [WILSON] Incremental Learning in Semantic Segmentation From Image Labels(CVPR 2022)[paper][code]
- [Connector] Towards Better Plasticity-Stability Trade-Off in Incremental Learning: A Simple Linear Connector(CVPR 2022)[paper][code]
- [PAD] Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization(CVPR 2022)[paper]
- [ERD] Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation(CVPR 2022)[paper][code]
- [AFC] Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation(CVPR 2022)[paper][code]
- [FACT] Forward Compatible Few-Shot Class-Incremental Learning(CVPR 2022)[paper][code]
- [L2P] Learning to Prompt for Continual Learning(CVPR 2022)[paper][code]
- [MEAT] Meta-attention for ViT-backed Continual Learning(CVPR 2022)[paper][code]
- [RCIL] Representation Compensation Networks for Continual Semantic Segmentation(CVPR 2022)[paper][code]
- [ZITS] Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding(CVPR 2022)[paper][code]
- [MTPSL] Learning Multiple Dense Prediction Tasks from Partially Annotated Data(CVPR 2022)[paper][code]
- [MMA] Modeling Missing Annotations for Incremental Learning in Object Detection(CVPR-Workshop 2022)[paper]
- [CoSCL] CoSCL: Cooperation of Small Continual
Learners is Stronger than a Big One(ECCV 2022)[paper][code]
- [AdNS] Balancing Stability and Plasticity through Advanced Null Space in Continual Learning(ECCV 2022)[paper]
- [ProCA] Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation(ECCV 2022)[paper][code]
- [R-DFCIL] R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning(ECCV 2022)[paper][code]
- [S3C] S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning(ECCV 2022)[paper][code]
- [H^2^] Helpful or Harmful: Inter-Task Association in Continual Learning(ECCV 2022)[paper]
- [DualPrompt] DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning(ECCV 2022)[paper]
- [ALICE] Few-Shot Class Incremental Learning From an Open-Set Perspective(ECCV 2022)[paper][code]
- [RU-TIL] Incremental Task Learning with Incremental Rank Updates(ECCV 2022)[paper][code]
- [FOSTER] FOSTER: Feature Boosti ng and Compression for Class-Incremental Learning(ECCV 2022)[paper]
- [SSR] Subspace Regularizers for Few-Shot Class Incremental Learning(ICLR 2022)[paper][code]
- [RGO] Continual Learning with Recursive Gradient Optimization(ICLR 2022)[paper]
- [TRGP] TRGP: Trust Region Gradient Projection for Continual Learning(ICLR 2022)[paper]
- [AGCN] AGCN: Augmented Graph Convolutional Network for Lifelong Multi-Label Image Recognition(ICME 2022)[paper][code]
- [WSN] Forget-free Continual Learning with Winning Subnetworks(ICML 2022)[paper][code]
- [NISPA] NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks(ICML 2022)[paper][code]
- [S-FSVI] Continual Learning via Sequential Function-Space Variational Inference(ICML 2022)[paper][code]
- [CUBER] Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer(NeurIPS 2022)[paper]
- [ADA] Memory Efficient Continual Learning with Transformers(NeurIPS 2022)[paper]
- [CLOM] Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation(NeurIPS 2022)[paper]
- [S-Prompt] S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning(NeurIPS 2022)[paper]
- [ALIFE] ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation(NIPS 2022)[paper]
- [PMT] Continual Learning In Environments With Polynomial Mixing Times(NIPS 2022)[paper]
- [STCISS] Self-training for class-incremental semantic segmentation(TNNLS 2022)[paper]
- [DSN] Dynamic Support Network for Few-shot Class Incremental Learning(TPAMI 2022)[paper]
- [MgSvF] MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning(TPAMI 2022)[paper]
- [TransIL] Dataset Knowledge Transfer for Class-Incremental Learning without Memory(WACV 2022)[paper]
- [NER-FSCIL] Few-Shot Class-Incremental Learning for Named Entity Recognition(ACL 2022)[paper]
- [LIMIT] Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks(arXiv 2022)[paper]
- [EMP] Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection(arXiv 2022)[paper]
- [SPTM] Class-Incremental Learning With Strong Pre-Trained Model(CVPR 2022)[paper]
- [BER] Bring Evanescent Representations to Life in Lifelong Class Incremental Learning(CVPR 2022)[paper]
- [Sylph] Sylph: A Hypernetwork Framework for Incremental Few-Shot Object Detection(CVPR 2022)[paper]
- [MetaFSCIL] MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning(CVPR 2022)[paper]
- [FCIL] Federated Class-Incremental Learning(CVPR 2022)[paper][code]
- [FILIT] Few-Shot Incremental Learning for Label-to-Image Translation(CVPR 2022)[paper]
- [PuriDivER] Online Continual Learning on a Contaminated Data Stream With Blurry Task Boundaries(CVPR 2022)[paper][code]
- [SNCL] Learning Bayesian Sparse Networks With Full Experience Replay for Continual Learning(CVPR 2022)[paper]
- [DVC] Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency(CVPR 2022)[paper][code]
- [CVS] Continual Learning for Visual Search With Backward Consistent Feature Embedding(CVPR 2022)[paper]
- [CPL] Continual Predictive Learning From Videos(CVPR 2022)[paper]
- [GCR] GCR: Gradient Coreset Based Replay Buffer Selection for Continual Learning(CVPR 2022)[paper]
- [LVT] Continual Learning With Lifelong Vision Transformer(CVPR 2022)[paper]
- [vCLIMB] vCLIMB: A Novel Video Class Incremental Learning Benchmark(CVPR 2022)[paper][code]
- [Learn-to-Imagine] Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data(CVPR 2022)[paper][code]
- [DCR] General Incremental Learning with Domain-aware Categorical Representations(CVPR 2022)[paper]
- [DIY-FSCIL] Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches(CVPR 2022)[paper]
- [C-FSCIL] Constrained Few-shot Class-incremental Learning(CVPR 2022)[paper][code]
- [SSRE] Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning(CVPR 2022)[paper]
- [CwD] Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning(CVPR 2022)[paper][code]
- [MSL] On Generalizing Beyond Domains in Cross-Domain Continual Learning(CVPR 2022)[paper]
- [DyTox] DyTox: Transformers for Continual Learning with DYnamic TOken Expansion(CVPR 2022)[paper][code]
- [X-DER] Class-Incremental Continual Learning into the eXtended DER-vers(ECCV 2022)[paper]
- [clsss-iNCD] Class-incremental Novel Class Discovery(ECCV 2022)[paper][code]
- [ARI] Anti-Retroactive Interference for Lifelong Learning(ECCV 2022)[paper][code]
- [Long-Tailed-CIL] Long-Tailed Class Incremental Learning(ECCV 2022)[paper][code]
- [LIRF] Learning with Recoverable Forgetting(ECCV 2022)[paper]
- [DSDM] Online Task-free Continual Learning with Dynamic Sparse Distributed Memory(ECCV 2022)[paper][code]
- [CVT] Online Continual Learning with Contrastive Vision Transformer(ECCV 2022)[paper]
- [TwF] Transfer without Forgetting(ECCV 2022)[paper][code]
- [CSCCT] Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer(ECCV 2022)[paper][code]
- [DLCFT] DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning(ECCV 2022)[paper]
- [ERDR] Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay(ECCV2022)[paper]
- [NCDwF] Novel Class Discovery without Forgetting(ECCV2022)[paper]
- [CoMPS] CoMPS: Continual Meta Policy Search(ICLR 2022)[paper]
- [i-fuzzy] Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference(ICLR 2022)[paper][code]
- [CLS-ER] Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System(ICLR 2022)[paper][code]
- [MRDC] Memory Replay with Data Compression for Continual Learning(ICLR 2022)[paper][code]
- [OCS] Online Coreset Selection for Rehearsal-based Continual Learning(ICLR 2022)[paper]
- [InfoRS] Information-theoretic Online Memory Selection for Continual Learning(ICLR 2022)[paper]
- [ER-AML] New Insights on Reducing Abrupt Representation Change in Online Continual Learning(ICLR 2022)[paper][code]
- [FAS] Continual Learning with Filter Atom Swapping(ICLR 2022)[paper]
- [LUMP] Rethinking the Representational Continuity: Towards Unsupervised Continual Learning(ICLR 2022)[paper]
- [CF-IL] Looking Back on Learned Experiences For Class/task Incremental Learning(ICLR 2022)[paper][code]
- [LFPT5] LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5(ICLR 2022)[paper][code]
- [Model Zoo] Model Zoo: A Growing Brain That Learns Continually(ICLR 2022)[paper]
- [OCM] Online Continual Learning through Mutual Information Maximization(ICML 2022)[paper][code]
- [DRO] Improving Task-free Continual Learning by Distributionally Robust Memory Evolution(ICML 2022)[paper][code]
- [EAK] Effects of Auxiliary Knowledge on Continual Learning(ICPR 2022)[paper]
- [RAR] Retrospective Adversarial Replay for Continual Learning(NeurIPS 2022)[paper]
- [LiDER] On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning(NeurIPS 2022)[paper]
- [SparCL] SparCL: Sparse Continual Learning on the Edge(NeurIPS 2022)[paper]
- [ClonEx-SAC] Disentangling Transfer in Continual Reinforcement Learning(NeurIPS 2022)[paper]
- [ODDL] Task-Free Continual Learning via Online Discrepancy Distance Learning(NeurIPS 2022)[paper]
- [CSSL] Continual semi-supervised learning through contrastive interpolation consistency(PRL 2022)[paper]
- [MBP] Model Behavior Preserving for Class-Incremental Learning(TNNLS 2022)[paper]
- [CandVot] Online Continual Learning via Candidates Voting(WACV 2022)[paper]
- [FlashCards] Knowledge Capture and Replay for Continual Learning(WACV 2022)[paper]
- [Meta-DR] Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning(CVPR 2021)[paper]
- [continual cross-modal retrieval] Continual learning in cross-modal retrieval(CVPR 2021)[paper]
- [DER] DER:Dynamically expandable representation for class incremental learning(CVPR 2021)[paper][code]
- [EFT] Efficient Feature Transformations for Discriminative and Generative Continual Learning(CVPR 2021)[paper][code]
- [PASS] Prototype Augmentation and Self-Supervision for Incremental Learning(CVPR 2021)[paper][code]
- [GeoDL] On Learning the Geodesic Path for Incremental Learning(CVPR 2021)[paper][code]
- [IL-ReduNet] Incremental Learning via Rate Reduction(CVPR 2021)[paper]
- [PIGWM] Image De-raining via Continual Learning(CVPR 2021)[paper]
- [BLIP] Continual Learning via Bit-Level Information Preserving(CVPR 2021)[paper][code]
- [Adam-NSCL] Training Networks in Null Space of Feature Covariance for Continual Learning(CVPR 2021)[paper][code]
- [PLOP] PLOP: Learning without Forgetting for Continual Semantic Segmentation(CVPR 2021)[paper][code]
- [SDR] Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations(CVPR 2021)[paper][code]
- [SKD] Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning(CVPR 2021)[paper]
- [SPB] Striking a balance between stability and plasticity for class-incremental learning(ICCV 2021)[paper]
- [Else-Net] Else-Net: Elastic Semantic Network for Continual Action Recognition from Skeleton Data(ICCV 2021)[paper]
- [LCwoF-Framework] Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting(ICCV 2021)[paper]
- [AFEC] AFEC: Active Forgetting of Negative Transfer in Continual Learning(NeurIPS 2021)[paper][code]
- [F2M] Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima(NeurIPS 2021)[paper][code]
- [NCL] Natural continual learning: success is a journey, not (just) a destination(NeurIPS 2021)[paper][code]
- [BCL] Formalizing the Generalization-Forgetting Trade-off in Continual Learning(NeurIPS 2021)[paper][code]
- [Posterior Meta-Replay] Posterior Meta-Replay for Continual Learning(NeurIPS 2021)[paper]
- [MARK] Optimizing Reusable Knowledge for Continual Learning via Metalearning(NeurIPS 2021)[paper][code]
- [Co-occur] Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection(NeurIPS 2021)[paper][code]
- [LINC] Lifelong and Continual Learning Dialogue Systems: Learning during Conversation(AAAI 2021)[paper]
- [CLNER] Continual learning for named entity recognition(AAAI 2021)[paper]
- [CLIS] A Continual Learning Framework for Uncertainty-Aware Interactive Image Segmentation(AAAI 2021)[paper]
- [PCL] Continual Learning by Using Information of Each Class Holistically(AAAI 2021)[paper]
- [MAS3] Unsupervised Model Adaptation for Continual Semantic Segmentation(AAAI 2021)[paper]
- [FSLL] Few-Shot Lifelong Learning(AAAI 2021)[paper]
- [VAR-GPs] Variational Auto-Regressive Gaussian Processes for Continual Learning(ICML 2021)[paper]
- [BSA] Bayesian Structural Adaptation for Continual Learning(ICML 2021)[paper]
- [GPM] Gradient projection memory for continual learning(ICLR 2021)[paper][code]
- [TMN] Triple-Memory Networks: A Brain-Inspired Method for Continual Learning(TNNLS 2021)[paper]
- [RKD] Few-Shot Class-Incremental Learning via Relation Knowledge Distillation(AAAI 2021)[paper]
- [AANets] Adaptive aggregation networks for class-incremental learning(CVPR 2021)[paper][code]
- [ORDisCo] ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning(CVPR 2021)[paper]
- [DDE] Distilling Causal Effect of Data in Class-Incremental Learning(CVPR 2021)[paper][code]
- [IIRC] IIRC: Incremental Implicitly-Refined Classification(CVPR 2021)[paper]
- [Hyper-LifelongGAN] Hyper-LifelongGAN: Scalable Lifelong Learning for Image Conditioned Generation(CVPR 2021)[paper]
- [CEC] Few-Shot Incremental Learning with Continually Evolved Classifiers(CVPR 2021)[paper]
- [iMTFA] Incremental Few-Shot Instance Segmentation(CVPR 2021)[paper]
- [RM] Rainbow memory: Continual learning with a memory of diverse samples(CVPR 2021)[paper]
- [LOGD] Layerwise Optimization by Gradient Decomposition for Continual Learning(CVPR 2021)[paper]
- [SPPR] Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning(CVPR 2021)[paper]
- [LReID] Lifelong Person Re-Identification via Adaptive Knowledge Accumulation(CVPR 2021)[paper][code]
- [SS-IL] SS-IL: Separated Softmax for Incremental Learning(ICCV 2021)[paper]
- [TCD] Class-Incremental Learning for Action Recognition in Videos(ICCV 2021)[paper]
- [CLOC] Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data(ICCV 2021)[paper][code]
- [CoPE] Continual Prototype Evolution:Learning Online from Non-Stationary Data Streams(ICCV 2021)[paper][code]
- [Co2L] Co2L: Contrastive Continual Learning(ICCV 2021)[paper][code]
- [SPR] Continual Learning on Noisy Data Streams via Self-Purified Replay(ICCV 2021)[paper]
- [NACL] Detection and Continual Learning of Novel Face Presentation Attacks(ICCV 2021)[paper]
- [Always Be Dreaming] Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning(ICCV 2021)[paper][code]
- [CL-HSCNet] Continual Learning for Image-Based Camera Localization(ICCV 2021)[paper][code]
- [RECALL] RECALL: Replay-based Continual Learning in Semantic Segmentation(ICCV 2021)[paper][code]
- [VAE] Synthesized Feature based Few-Shot Class-Incremental Learning on a Mixture of Subspaces(ICCV 2021)[paper]
- [ERT] Rethinking Experience Replay: a Bag of Tricks for Continual Learning(ICPR 2021)[paper][code]
- [KCL] Kernel Continual Learning(ICML 2021)[paper][code]
- [MLIOD] Incremental Object Detection via Meta-Learning(TPAMI 2021)[paper][code]
- [BNS] BNS: Building Network Structures Dynamically for Continual Learning(NeurIPS 2021)[paper]
- [FS-DGPM] Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning(NeurIPS 2021)[paper]
- [SSUL] SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning(NeurIPS 2021)[paper]
- [DualNet] DualNet: Continual Learning, Fast and Slow(NeurIPS 2021)[paper]
- [classAug] Class-Incremental Learning via Dual Augmentation(NeurIPS 2021)[paper]
- [GMED] Gradient-based Editing of Memory Examples for Online Task-free Continual Learning(NeurIPS 2021)[paper]
- [BooVAE] BooVAE: Boosting Approach for Continual Learning of VAE(NeurIPS 2021)[paper][code]
- [GeMCL] Generative vs. Discriminative: Rethinking The Meta-Continual Learning(NeurIPS 2021)[paper]
- [RMM] RMM: Reinforced Memory Management for Class-Incremental Learning(NIPS 2021)[paper][code]
- [LSF] Learning with Selective Forgetting(IJCAI 2021)[paper]
- [ASER] Online Class-Incremental Continual Learning with Adversarial Shapley Value(AAAI 2021)[paper][code]
- [CML] Curriculum-Meta Learning for Order-Robust Continual Relation Extraction(AAAI 2021)[paper][code]
- [HAL] Using Hindsight to Anchor Past Knowledge in Continual Learning(AAAI 2021)[paper]
- [MDMT] Multi-Domain Multi-Task Rehearsal for Lifelong Learning(AAAI 2021)[paper]
- [AU] Do Not Forget to Attend to Uncertainty While Mitigating Catastrophic Forgetting(WACV 2021)[paper]
- [IDBR] Continual Learning for Text Classification with Information Disentanglement Based Regularization(NAACL 2021)[paper][code]
- [COIL] Co-Transport for Class-Incremental Learning(ACM MM 2021)[paper]
2020
- [CWR*] Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches(CVPR 2020)[paper]
- [MiB] Modeling the Background for Incremental Learning in Semantic Segmentation(CVPR 2020)[paper][code]
- [K-FAC] Continual Learning with Extended Kronecker-factored Approximate Curvature(CVPR 2020)[paper]
- [SDC] Semantic Drift Compensation for Class-Incremental Learning(CVPR 2020)[paper][code]
- [NLTF] Incremental Multi-Domain Learning with Network Latent Tensor Factorization(AAAI 2020)[paper]
- [CLCL] Compositional Continual Language Learning(ICLR 2020)[paper][code]
- [APD] Scalable and Order-robust Continual Learning with Additive Parameter Decomposition(ICLR 2020)[paper]
- [HYPERCL] Continual learning with hypernetworks(ICLR 2020)[paper][code]
- [CN-DPM] A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning(ICLR 2020)[paper]
- [UCB] Uncertainty-guided Continual Learning with Bayesian Neural Networks(ICLR 2020)[paper][code]
- [CLAW] Continual Learning with Adaptive Weights(ICLR 2020)[paper]
- [CAT] Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks(NeurIPS 2020)[paper][code]
- [AGS-CL] Continual Learning with Node-Importance based Adaptive Group Sparse Regularization(NeurIPS 2020)[paper]
- [MERLIN] Meta-Consolidation for Continual Learning(NeurIPS 2020)[paper][code]
- [OSAKA] Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning(NeurIPS 2020)[paper][code]
- [RATT] RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning(NeurIPS 2020)[paper]
- [CCLL] Calibrating CNNs for Lifelong Learning(NeurIPS 2020)[paper]
- [CIDA] Class-Incremental Domain Adaptation(ECCV 2020)[paper]
- [GraphSAIL] GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems(CIKM 2020)[paper]
- [ANML] Learning to Continually Learn(ECAI 2020)[paper][code]
- [ICWR] Initial Classifier Weights Replay for Memoryless Class Incremental Learning(BMVC 2020)[paper]
- [DAM] Incremental Learning Through Deep Adaptation(TPAMI 2020)[paper]
- [OGD] Orthogonal Gradient Descent for Continual Learning(PMLR 2020)[paper]
- [MC-OCL] Online Continual Learning under Extreme Memory Constraints(ECCV2020)[paper][code]
- [RCM] Reparameterizing convolutions for incremental multi-task learning without task interference(ECCV 2020)[paper][code]
- [OvA-INN] OvA-INN: Continual Learning with Invertible Neural Networks(IJCNN 2020)[paper]
- [XtarNet] XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning(ICLM 2020)[paper][code]
- [DMC] Class-incremental learning via deep model consolidation(WACV 2020)[paper]
- [iTAML] iTAML : An Incremental Task-Agnostic Meta-learning Approach(CVPR 2020)[paper][code]
- [FSCIL] Few-Shot Class-Incremental Learning(CVPR 2020)[paper][code]
- [GFR] Generative feature replay for class-incremental learning(CVPR 2020)[paper][code]
- [OSIL] Incremental Learning In Online Scenario(CVPR 2020)[paper]
- [ONCE] Incremental Few-Shot Object Detection(CVPR 2020)[paper]
- [WA] Maintaining discrimination and fairness in class incremental learning(CVPR 2020)[paper][code]
- [CGATE] Conditional Channel Gated Networks for Task-Aware Continual Learning(CVPR 2020)[paper][code]
- [Mnemonics Training] Mnemonics Training: Multi-Class Incremental Learning without Forgetting(CVPR 2020)[paper][code]
- [MEGA] Improved schemes for episodic memory based lifelong learning algorithm(NeurIPS 2020)[paper]
- [GAN Memory] GAN Memory with No Forgetting(NeurIPS 2020)[paper][code]
- [Coreset] Coresets via Bilevel Optimization for Continual Learning and Streaming(NeurIPS 2020)[paper]
- [FROMP] Continual Deep Learning by Functional Regularisation of Memorable Past(NeurIPS 2020)[paper][code]
- [DER] Dark Experience for General Continual Learning: a Strong, Simple Baseline(NeurIPS 2020)[paper][code]
- [InstAParam] Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization(NeurIPS 2020)[paper]
- [BOCL] Bi-Objective Continual Learning: Learning "New" While Consolidating "Known"(AAAI 2020)[paper]
- [REMIND] Remind your neural network to prevent catastrophic forgetting(ECCV 2020)[paper][code]
- [ACL] Adversarial Continual Learning(ECCV 2020)[paper][code]
- [TPCIL] Topology-Preserving Class-Incremental Learning(ECCV 2020)[paper]
- [GDumb] GDumb:A simple approach that questions our progress in continual learning(ECCV 2020)[paper][code]
- [PRS] Imbalanced Continual Learning with Partitioning Reservoir Sampling(ECCV 2020)[paper]
- [PODNet] Pooled Outputs Distillation for Small-Tasks Incremental Learning(ECCV 2020)[paper][code]
- [FA] Memory-Efficient Incremental Learning Through Feature Adaptation(ECCV 2020)[paper]
- [L-VAEGAN] Learning latent representions across multiple data domains using Lifelong VAEGAN(ECCV 2020)[paper]
- [Piggyback GAN] Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation(ECCV 2020)[paper][code]
- [IDA] Incremental Meta-Learning via Indirect Discriminant Alignment(ECCV 2020)[paper]
- [RCM] Reparameterizing Convolutions for Incremental Multi-Task Learning Without Task Interference(ECCV 2020)[paper]
- [LAMOL] LAMOL: LAnguage MOdeling for Lifelong Language Learning(ICLR 2020)[paper][code]
- [FRCL] Functional Regularisation for Continual Learning with Gaussian Processes(ICLR 2020)[paper][code]
- [GRS] Continual Learning with Bayesian Neural Networks for Non-Stationary Data(ICLR 2020)[paper]
- [Brain-inspired replay] Brain-inspired replay for continual learning with artificial neural networks(Natrue Communications 2020)[paper][code]
- [ScaIL] ScaIL: Classifier Weights Scaling for Class Incremental Learning(WACV 2020)[paper][code]
- [CLIFER] CLIFER: Continual Learning with Imagination for Facial Expression Recognition(FG 2020)[paper]
- [ARPER] Continual Learning for Natural Language Generation in Task-oriented Dialog Systems(EMNLP 2020)[paper]
- [DnR] Distill and Replay for Continual Language Learning(COLING 2020)[paper]
- [ADER] ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation(RecSys 2020)[paper][code]
- [MUC] More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning(ECCV 2020)[paper][code]
2019
- [LwM] Learning without memorizing(CVPR 2019)[paper]
- [CPG] Compacting, picking and growing for unforgetting continual learning(NeurIPS 2019)[paper][code]
- [UCL] Uncertainty-based continual learning with adaptive regularization(NeurIPS 2019)[paper]
- [OML] Meta-Learning Representations for Continual Learning(NeurIPS 2019)[paper][code]
- [ALASSO] Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation(ICCV 2019)[paper]
- [Learn-to-Grow] Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting(PMLR 2019)[paper]
- [OWM] Continual Learning of Context-dependent Processing in Neural Networks(Nature Machine Intelligence 2019)[paper][code]
- [LUCIR] Learning a Unified Classifier Incrementally via Rebalancing(CVPR 2019)[paper][code]
- [TFCL] Task-Free Continual Learning(CVPR 2019)[paper]
- [GD-WILD] Overcoming catastrophic forgetting with unlabeled data in the wild(CVPR 2019)[paper][code]
- [DGM] Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning(CVPR 2019)[paper]
- [BiC] Large Scale Incremental Learning(CVPR 2019)[paper][code]
- [MER] Learning to learn without forgetting by maximizing transfer and minimizing interference(ICLR 2019)[paper][code]
- [PGMA] Overcoming catastrophic forgetting for continual learning via model adaptation(ICLR 2019)[paper]
- [A-GEM] Efficient Lifelong Learning with A-GEM(ICLR 2019)[paper][code]
- [IL2M] Class incremental learning with dual memory(ICCV 2019)[paper]
- [ILCAN] Incremental learning using conditional adversarial networks(ICCV 2019)[paper]
- [Lifelong GAN] Lifelong GAN: Continual Learning for Conditional Image Generation(ICCV 2019)[paper]
- [GSS] Gradient based sample selection for online continual learning(NIPS 2019)[paper]
- [ER] Experience Replay for Continual Learning(NIPS 2019)[paper]
- [MIR] Online Continual Learning with Maximal Interfered Retrieval(NIPS 2019)[paper][code]
- [RPS-Net] Random Path Selection for Incremental Learning(NIPS 2019)[paper]
- [CLEER] Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay(IJCAI 2019)[paper]
- [PAE] Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning(ICMR 2019)[paper][code]
2018
- [PackNet] PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning(CVPR 2018)[paper][code]
- [OLA] Online Structured Laplace Approximations for Overcoming Catastrophic Forgetting(NIPS 2018)[paper]
- [RCL] Reinforced Continual Learning(NIPS 2018)[paper][code]
- [MARL] Routing networks: Adaptive selection of non-linear functions for multi-task learning(ICLR 2018)[paper]
- [P&C] Progress & Compress: A scalable framework for continual learning(ICML 2018)[paper]
- [DEN] Lifelong Learning with Dynamically Expandable Networks(ICLR 2018)[paper][code]
- [Piggyback] Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights(ECCV 2018)[paper][code]
- [RWalk] Riemanian Walk for Incremental Learning: Understanding Forgetting and Intransigence(ECCV 2018)[paper]
- [MAS] Memory Aware Synapses: Learning What not to Forget(ECCV 2018)[paper][code]
- [R-EWC] Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting(ICPR 2018)[paper][code]
- [HAT] Overcoming Catastrophic Forgetting with Hard Attention to the Task(PMLR 2018)[paper][code]
- [MeRGANs] Memory Replay GANs:learning to generate images from new categories without forgetting(NIPS 2018)[paper][code]
- [EEIL] End-to-End Incremental Learning(ECCV 2018)[paper][code]
- [Adaptation by Distillation] Lifelong Learning via Progressive Distillation and Retrospection(ECCV 2018)[paper]
- [ESGR] Exemplar-Supported Generative Reproduction for Class Incremental Learning(BMVC 2018)[paper][code]
- [VCL] Variational Continual Learning(ICLR 2018)[paper]
- [FearNet] FearNet: Brain-Inspired Model for Incremental Learning(ICLR 2018)[paper]
- [DGDMN] Deep Generative Dual Memory Network for Continual Learning(ICLR 2018)[paper]
2017
- [Expert Gate] Expert Gate: Lifelong learning with a network of experts(CVPR 2017)[paper][code]
- [ILOD] Incremental Learning of Object Detectors without Catastrophic Forgetting(ICCV 2017)[paper][code]
- [EBLL] Encoder Based Lifelong Learning(ICCV2017)[paper]
- [IMM] Overcoming Catastrophic Forgetting by Incremental Moment Matching(NIPS 2017)[paper][code]
- [SI] Continual Learning through Synaptic Intelligence(ICML 2017)[paper][code]
- [EWC] Overcoming Catastrophic Forgetting in Neural Networks(PNAS 2017)[paper][code]
- [iCARL] iCaRL: Incremental Classifier and Representation Learning(CVPR 2017)[paper][code]
- [GEM] Gradient Episodic Memory for Continual Learning(NIPS 2017)[paper][code]
- [DGR] Continual Learning with Deep Generative Replay(NIPS 2017)[paper][code]