There are 2 repositories under class-incremental-learning topic.
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
PyTorch implementation of AANets (CVPR 2021) and Mnemonics Training (CVPR 2020 Oral)
A collection of online continual learning paper implementations and tricks for computer vision in PyTorch, including our ASER(AAAI-21), SCR(CVPR21-W) and an online continual learning survey (Neurocomputing).
Class-Incremental Learning: A Survey (TPAMI 2024)
Forward Compatible Few-Shot Class-Incremental Learning (CVPR'22)
The code repository for "Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need" in PyTorch.
a PyTorch Tutorial to Class-Incremental Learning | a Distributed Training Template of CIL with core code less than 100 lines.
[ICLR 2023] The official code for our ICLR 2023 (top25%) paper: "Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning"
PyTorch implementation of a VAE-based generative classifier, as well as other class-incremental learning methods that do not store data (DGR, BI-R, EWC, SI, CWR, CWR+, AR1, the "labels trick", SLDA).
The official implementation for ECCV22 paper: "FOSTER: Feature Boosting and Compression for Class-Incremental Learning" in PyTorch.
The code repository for "A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning" (ICLR'23) in PyTorch
The code repository for "Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks" (TPAMI 2023) in PyTorch.
Code for the ICLR2022 paper on Subspace Regularization for few-shot class incremental image classification
✌[ICLR 2024] Class Incremental Learning via Likelihood Ratio Based Task Prediction
(AAAI 2021) Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network
Official Implementation of the ECCV 2022 Paper "Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer"
[CVPR'22] Official Implementation of "CNLL: A Semi-supervised Approach for Continual Noisy Label Learning"
The code repository for "Co-Transport for Class-Incremental Learning" (ACM MM'21) in PyTorch.
The official code for our paper "Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants".
Simple data and training pipeline for class-incremental method :smile:
Class Incremental Learning (iCaRL, EEIL, BiC) reproduce github repository.
Adaptive Decision Forest(ADF) is an incremental machine learning framework called to produce a decision forest to classify new records. ADF is capable to classify new records even if they are associated with previously unseen classes. ADF also is capable of identifying and handling concept drift; it, however, does not forget previously gained knowledge. Moreover, ADF is capable of handling big data if the data can be divided into batches.
[TMLR 22] "Queried Unlabeled Data Improves and Robustifies Class- Incremental Learning" by Tianlong Chen, Sijia Liu, Shiyu Chang, Lisa Animi, Zhangyang Wang