OpenMMLab Model Deployment Framework

A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and other exciting features.

[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021

Object detection with multi-level representations generated from deep high-resolution representation learning (HRNetV2h). This is an official implementation for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919

mmdetection源码注释

convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.

[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation

The First Place Solution of Kaggle iMaterialist (Fashion) 2019 at FGVC6

USB: Universal-Scale Object Detection Benchmark (BMVC 2022)

Official code of the paper "ReDet: A Rotation-Equivariant Detector for Aerial Object Detection" (CVPR 2021)

[ICCV 2021] Instances as Queries

A toolbox for box-supervised instance segmentation.

Official code of the paper "Align Deep Features for Oriented Object Detection"

This is an implementation of zero-shot instance segmentation using Segment Anything.

[CVPR2023 Highlight] Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection

SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)

SWA Object Detection

icip2022 paper: sahi benchmark on visdrone and xview datasets using fcos, vfnet and tood detectors

和鲸社区Kesci 水下目标检测算法赛（光学图像赛项）三等奖 单模方案

[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer