Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

OpenMMLab Model Deployment Framework

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

Neural Network Compression Framework for enhanced OpenVINO™ inference

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

mmdetection源码注释

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

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

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

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

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

A toolbox for box-supervised instance segmentation.

[ICCV 2021] Instances as Queries

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

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

[WACV2022] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

SWA Object Detection

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