BoxInst: High-Performance Instance Segmentation with Box Annotations

Last update: Dec 21, 2022

Related tags

Overview

Introduction

This repository is the code that needs to be submitted for OpenMMLab Algorithm Ecological Challenge, the paper is BoxInst: High-Performance Instance Segmentation with Box Annotations

License

This project is released under the Apache 2.0 license.

Benchmark and model zoo

BoxInst (CVPR'2021)
ConInst (ECCV'2020)

BoxInst

Name	box AP	mask AP	log	download
BoxInst_MS_R_50_1x	0.390	0.304	log	model
BoxInst_MS_R_50_90k	0.388	0.302	log	model
BoxInst_MS_R_101_90k	0.410	0.318	-	model

Some other methods in MMDetection are also supported.

Getting Started

Our project is totally based on MMCV and MMDetection. Please see get_started.md for the basic usage of MMDetection.

Train

Please see doc to start training. Example,

CUDA_VISIBLE_DEVICES=0,1,2,3 PORT=29500 ./tools/dist_train.sh configs/boxinst/boxinst_r50_caffe_fpn_coco_mstrain_1x.py 4

please following linear linear scaling rule to adjust batch size, learning rate and iterations.

Inference and Eval

python tools/test.py configs/boxinst/boxinst_r50_caffe_fpn_coco_mstrain_1x.py work_dirs/boxinst_r50_caffe_fpn_coco_mstrain_1x.py/latest.pth --eval bbox segm

Acknowledgement

MMCV: OpenMMLab foundational library for computer vision.
MMDetection: OpenMMLab detection toolbox and benchmark.

BoxInst: High-Performance Instance Segmentation with Box Annotations

Related tags

Overview

Introduction

License

Benchmark and model zoo

BoxInst

Getting Started

Train

Inference and Eval

Acknowledgement

Owner

You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling

Fully convolutional deep neural network to remove transparent overlays from images

The personal repository of the work: DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer.

General Vision Benchmark, a project from OpenGVLab

Official PyTorch Implementation of Learning Architectures for Binary Networks

Code for "Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation". [AAAI 2021]

A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) based on Deep Filtering.

Mengzi Pretrained Models

[IROS'21] SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning

The missing CMake project initializer

Model Zoo for MindSpore

Source Code for our paper: Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network

Apply AnimeGAN-v2 across frames of a video clip

B2EA: An Evolutionary Algorithm Assisted by Two Bayesian Optimization Modules for Neural Architecture Search

Codes for AAAI 2022 paper: Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs

Build Graph Nets in Tensorflow

A python library to build Model Trees with Linear Models at the leaves.

Method for facial emotion recognition compitition of Xunfei and Datawhale .

Instance-level Image Retrieval using Reranking Transformers

Technical Analysis library in pandas for backtesting algotrading and quantitative analysis

BoxInst: High-Performance Instance Segmentation with Box Annotations

Related tags

Overview

Introduction

License

Benchmark and model zoo

BoxInst

Getting Started

Train

Inference and Eval

Acknowledgement

Owner

You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling

Fully convolutional deep neural network to remove transparent overlays from images

The personal repository of the work: *DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer*.

General Vision Benchmark, a project from OpenGVLab

Official PyTorch Implementation of Learning Architectures for Binary Networks

Code for "Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation". [AAAI 2021]

A Low Complexity Speech Enhancement Framework for Full-Band Audio (48kHz) based on Deep Filtering.

Mengzi Pretrained Models

[IROS'21] SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning

The missing CMake project initializer

Model Zoo for MindSpore

Source Code for our paper: Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network

Apply AnimeGAN-v2 across frames of a video clip

B2EA: An Evolutionary Algorithm Assisted by Two Bayesian Optimization Modules for Neural Architecture Search

Codes for AAAI 2022 paper: Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs

Build Graph Nets in Tensorflow

A python library to build Model Trees with Linear Models at the leaves.

Method for facial emotion recognition compitition of Xunfei and Datawhale .

Instance-level Image Retrieval using Reranking Transformers

Technical Analysis library in pandas for backtesting algotrading and quantitative analysis

The personal repository of the work: DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer.