vignywang

SAMFeat

The official implementation of “Segment Anything Model is a Good Teacher for Local Feature Learning”.

Awesome-Local-Feature-Matching

AWDesc

MTLDesc

CNDesc

Pytorch-CGANet

TRFeat

Triple Robustness Augmentation Local Features for Multi-source Image Registration

IDC

Exploring Intrinsic Discrimination and Consistency for Weakly Supervised Object Localization

TMT

The official implementation of “Token Masking Transformer for Weakly Supervised Object Localization”

AlgorithmAndDataStructure

互联网行业研发岗面试必备算法题配图解析及代码

RepresentationLearning

Representation Learning and Representation Fusion for computer vision, semantic scene understanding, and robotics.

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

SuperPoint

Efficient neural feature detector and descriptor

torch-cam

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

AWDesc1

CVPR2022-Paper-Code-Interpretation

cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

eg3d

LFD-A-Light-and-Fast-Detector

LFD is a big update upon LFFD. Generally, LFD is a multi-class object detector characterized by lightweight, low inference latency and superior precision. It is for real-world appilcations.

LoFTR

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021

Mask2Former

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

natural-language-joint-query-search

Search photos on Unsplash based on OpenAI's CLIP model, support search with joint image+text queries and attention visualization.

PoSFeat

[CVPR2022] Decoupling Makes Weakly Supervised Local Feature Better

Reading-List-1

Reading list on deep learning

SGMNet

Implementation of "Learning to Match Features with Seeded Graph Matching Network" ICCV2021

TS-CAM

Codes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.