9 open source projects by Megvii-BaseDetection

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

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

End-to-End Object Detection with Fully Convolutional Network

Learning Dynamic Routing for Semantic Segmentation

All-in-one Toolbox for Computer Vision Research.

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

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

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

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