Yujin Lee's repositories
Uniformaly
Uniformaly: Towards Task-Agnostic Unified Anomaly Detection
paper_review
paper review archive
Awesome-Open-Vocabulary
A Survey on Open Vocabulary Learning
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
CLIPSelf
[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
DALLE2-pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
denoising-diffusion-pytorch
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
detr
End-to-End Object Detection with Transformers
FFCV-SSL
FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
MOOD
Official PyTorch implementation and pretrained models of Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling Is All You Need (MOOD in short). Our paper is accepted by CVPR2023.
OFA
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
open_flamingo
An open-source framework for training large multimodal models.
OWOD
(CVPR 2021 Oral) Open World Object Detection
PANDA
PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation (CVPR 2021)
patchcore-inspection
patchcore for visual inspection
poolformer
PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)
PromptAD
Official implementation of CVPR 2024 PromptAD: Learning Prompts with Only Normal Samples for Few-Shot Anomaly Detection
SimCLR-1
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
UniAD_species
Extension code for Multi-class Anomaly Detection with species dataset
visual_token_matching
[ICLR'23 Oral] Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching