Stars
DAMO-YOLO: a fast and accurate object detection method wi 10000 th some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.
1st place solution to the Satellite Remote Sensing Image Change Detection Challenge hosted by SenseTime
The 1st Place Solution of the Google Landmark 2019 Retrieval Challenge and the 3rd Place Solution of the Recognition Challenge.
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
Code for the CVPR2021 paper "Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition"
Official repository for VIGOR : Cross-View Image Geo-localization beyond One-to-one Retrieval
ELECTRICITY: An Efficient Multi-camera Vehicle Tracking System for Intelligent City(CVPR 2020 AI City Challenge Track 3)
Implementations of few-shot object detection benchmarks
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
End-to-End Object Detection with Transformers
Open-source stronger baseline for unsupervised or domain adaptive object re-ID.
Style guides for Google-originated open-source projects
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
Implementation of "Spectral Feature Tansformation for Person Re-identification"
OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features
Implementation of One-Shot Object Detection with Co-Attention and Co-Excitation in Pytorch
Expanded Cross Neighborhood distance based Re-ranking (ECN)