YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/BEVDepth
Official code for BEVDepth.cvpods
All-in-one Toolbox for Computer Vision Research.DeFCN
End-to-End Object Detection with Fully Convolutional NetworkBorderDet
BorderDet: Border Feature for Dense Object Detection(ECCV2020 Oral)DynamicRouting
Learning Dynamic Routing for Semantic SegmentationBEVStereo
Official code for BEVStereoOTA
Official implementation of our CVPR2021 paper "OTA: Optimal Transport Assignment for Object Detection" in Pytorch.AutoAssign
Pytorch implementation of "AutoAssign: Differentiable Label Assignment for Dense Object Detection"TreeFilter-Torch
Learnable Tree Filter for Structure-preserving Feature TransformDenseTeacher
DenseTeacher: Dense Pseudo-Label for Semi-supervised Object DetectionDisAlign
Implementation of "Distribution Alignment: A Unified Framework for Long-tail Visual Recognition"(CVPR 2021)Megvii-BaseDetection
You are welcomed to join us!GFSD
This project provides an implementation for "Generalized Few-Shot Object Detection without Forgetting" (CVPR2021) on PyTorch.LLA
Official implementation of our paper "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" in Pytorch.4K-Face
4K-Face: A Dataset with Huge Scale-variance Facesstorage
provide Checkpoint for users.Love Open Source and this site? Check out how you can help us