Owner

Megvii-BaseDetection

15 indexed repositories · View on GitHub

• YOLOX

  YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documenta...

  Python · 10627 stars

• BEVDepth

  Official code for BEVDepth.

  Python · 881 stars

• cvpods

  All-in-one Toolbox for Computer Vision Research.

  Python · 663 stars

• DeFCN

  End-to-End Object Detection with Fully Convolutional Network

  Python · 495 stars

• BorderDet

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

  Python · 429 stars

• DynamicRouting

  Learning Dynamic Routing for Semantic Segmentation

  Python · 380 stars

• BEVStereo

  Official code for BEVStereo

  Python · 282 stars

• OTA

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

  Python · 246 stars

• AutoAssign

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

  Python · 144 stars

• TreeFilter-Torch

  Learnable Tree Filter for Structure-preserving Feature Transform

  Python · 144 stars

• DenseTeacher

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

  Python · 131 stars

• DisAlign

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

  Python · 118 stars

• GFSD

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

  Python · 50 stars

• 4K-Face

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

  40 stars

• LLA

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

  Python · 36 stars