MMDetection: Open MMLab Detection Toolbox and Benchmark

TL;DR

MMDetection is a comprehensive, open-source object detection toolbox that includes numerous models, components, and benchmarking tools, aiming to support research and development in object detection.

Contribution

It introduces a unified, feature-rich detection platform with extensive model weights and benchmarking capabilities, evolving from a winning codebase to a complete detection toolbox.

Findings

Contains over 200 network models with pre-trained weights

Provides extensive benchmarking results for various detection methods

Supports flexible reimplementation and development of new detectors

Abstract

We present MMDetection, an object detection toolbox that contains a rich set of object detection and instance segmentation methods as well as related components and modules. The toolbox started from a codebase of MMDet team who won the detection track of COCO Challenge 2018. It gradually evolves into a unified platform that covers many popular detection methods and contemporary modules. It not only includes training and inference codes, but also provides weights for more than 200 network models. We believe this toolbox is by far the most complete detection toolbox. In this paper, we introduce the various features of this toolbox. In addition, we also conduct a benchmarking study on different methods, components, and their hyper-parameters. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new detectors. Code and models are available at https://github.com/open-mmlab/mmdetection. The project is under active development and we will keep this document updated.