YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

YOLOX is a Python library that automatically draws labeled boxes around objects in images and video in real time, offering model sizes from phone-friendly Nano to GPU-powered Extra-Large, without needing pre-defined anchor boxes.

Official code for BEVDepth.

All-in-one Toolbox for Computer Vision Research.

End-to-End Object Detection with Fully Convolutional Network

BorderDet: Border Feature for Dense Object Detection(ECCV2020 Oral)

Learning Dynamic Routing for Semantic Segmentation

Official code for BEVStereo

Official implementation of our CVPR2021 paper "OTA: Optimal Transport Assignment for Object Detection" in Pytorch.

Learnable Tree Filter for Structure-preserving Feature Transform

Pytorch implementation of "AutoAssign: Differentiable Label Assignment for Dense Object Detection"

DenseTeacher: Dense Pseudo-Label for Semi-supervised Object Detection

Implementation of "Distribution Alignment: A Unified Framework for Long-tail Visual Recognition"(CVPR 2021)

You are welcomed to join us!

This project provides an implementation for "Generalized Few-Shot Object Detection without Forgetting" (CVPR2021) on PyTorch.

4K-Face: A Dataset with Huge Scale-variance Faces

Official implementation of our paper "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" in Pytorch.

provide Checkpoint for users.