MMDetection: Open MMLab Detection Toolbox and Benchmark (2019-06-17T00:00:00.000000Z)

TL;DR

This paper presents MMDetection, an object detection toolbox that contains a rich set of object detection and instance segmentation methods as well as related components and modules, and conducts a benchmarking study on different methods, components, and their hyper-parameters.

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 this https URL. The project is under active development and we will keep this document updated.

Authors

References43 items

Grid R-CNN

GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond

Rethinking Classification and Localization for Object Detection

Double-Head RCNN: Rethinking Classification and Localization for Object Detection

An Empirical Study of Spatial Attention Mechanisms in Deep Networks

High-Resolution Representations for Labeling Pixels and Regions

Libra R-CNN: Towards Balanced Learning for Object Detection

FCOS: Fully Convolutional One-Stage Object Detection

Weight Standardization

Feature Selective Anchor-Free Module for Single-Shot Object Detection

SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition

Mask Scoring R-CNN

Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression

Deep High-Resolution Representation Learning for Human Pose Estimation

Hybrid Task Cascade for Instance Segmentation

Region Proposal by Guided Anchoring

Scale-Aware Trident Networks for Object Detection

Grid R-CNN

Deformable ConvNets V2: More Deformable, Better Results

Rethinking ImageNet Pre-Training

Gradient Harmonized Single-stage Detector

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch

Group Normalization

Cascade R-CNN: Delving Into High Quality Object Detection

MegDet: A Large Mini-Batch Object Detector

Improving Object Localization with Fitness NMS and Bounded IoU Loss

Automatic differentiation in PyTorch

Mixed Precision Training

Focal Loss for Dense Object Detection

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Soft-NMS — Improving Object Detection with One Line of Code

Mask R-CNN

Deformable Convolutional Networks

Aggregated Residual Transformations for Deep Neural Networks

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Training Region-Based Object Detectors with Online Hard Example Mining

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Fast R-CNN

maskrcnn-benchmark: Fast, modular reference implementation of instance segmentation and object detection algorithms in pytorch

TL;DR

Abstract

Authors

References43 items

Grid R-CNN

GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond

Rethinking Classification and Localization for Object Detection

Double-Head RCNN: Rethinking Classification and Localization for Object Detection

An Empirical Study of Spatial Attention Mechanisms in Deep Networks

High-Resolution Representations for Labeling Pixels and Regions

Libra R-CNN: Towards Balanced Learning for Object Detection

FCOS: Fully Convolutional One-Stage Object Detection

Weight Standardization

Feature Selective Anchor-Free Module for Single-Shot Object Detection

SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition

Mask Scoring R-CNN

Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression

Deep High-Resolution Representation Learning for Human Pose Estimation

Hybrid Task Cascade for Instance Segmentation

Region Proposal by Guided Anchoring

Scale-Aware Trident Networks for Object Detection

Grid R-CNN

Deformable ConvNets V2: More Deformable, Better Results

Rethinking ImageNet Pre-Training

Gradient Harmonized Single-stage Detector

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch

Group Normalization

Cascade R-CNN: Delving Into High Quality Object Detection

MegDet: A Large Mini-Batch Object Detector

Improving Object Localization with Fitness NMS and Bounded IoU Loss

Automatic differentiation in PyTorch

Mixed Precision Training

Focal Loss for Dense Object Detection

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Soft-NMS — Improving Object Detection with One Line of Code

Mask R-CNN

Deformable Convolutional Networks

Aggregated Residual Transformations for Deep Neural Networks

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Training Region-Based Object Detectors with Online Hard Example Mining

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Fast R-CNN

maskrcnn-benchmark: Fast, modular reference implementation of instance segmentation and object detection algorithms in pytorch

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names