RefineMask (CVPR 2021)

Last update: Jan 07, 2023

Related tags

Overview

RefineMask: Towards High-Quality Instance Segmentation
with Fine-Grained Features (CVPR 2021)

This repo is the official implementation of RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features.

Framework

Main Results

Results on COCO

Method	Backbone	Schedule	AP	AP^*	Checkpoint
Mask R-CNN	R50-FPN	1x	34.7	36.8
RefineMask	R50-FPN	1x	37.3	40.6	download
Mask R-CNN	R50-FPN	2x	35.4	37.7
RefineMask	R50-FPN	2x	37.8	41.2	download
Mask R-CNN	R101-FPN	1x	36.1	38.4
RefineMask	R101-FPN	1x	38.6	41.8	download
Mask R-CNN	R101-FPN	2x	36.6	39.3
RefineMask	R101-FPN	2x	39.0	42.4	download

Note: No data augmentations except standard horizontal flipping were used.

Results on LVIS

Method	Backbone	Schedule	AP	AP_r	AP_c	AP_f	Checkpoint
Mask R-CNN	R50-FPN	1x	22.1	10.1	21.7	30.0
RefineMask	R50-FPN	1x	25.7	13.8	24.9	31.8	download
Mask R-CNN	R101-FPN	1x	23.7	12.3	23.2	29.1
RefineMask	R101-FPN	1x	27.1	15.6	26.2	33.1	download

Results on Cityscapes

Method	Backbone	Schedule	AP	AP_S	AP_M	AP_L	Checkpoint
Mask R-CNN	R50-FPN	1x	33.8	12.0	31.5	51.8
RefineMask	R50-FPN	1x	37.6	14.0	35.4	57.9	download

Efficiency of RefineMask

Method	AP	AP^*	FPS
Mask R-CNN	34.7	36.8	15.7
PointRend	35.6	38.7	11.4
HTC	37.4	40.7	4.4
RefineMask	37.3	40.9	11.4

Usage

Requirements

Python 3.6+
Pytorch 1.5.0
mmcv-full 1.0.5

Datasets

data
  ├── coco
  |   ├── annotations
  │   │   │   ├── instances_train2017.json
  │   │   │   ├── instances_val2017.json
  │   │   │   ├── lvis_v0.5_val_cocofied.json
  │   ├── train2017
  │   │   ├── 000000004134.png
  │   │   ├── 000000031817.png
  │   │   ├── ......
  │   ├── val2017
  │   ├── test2017
  ├── lvis
  |   ├── annotations
  │   │   │   ├── lvis_v1_train.json
  │   │   │   ├── lvis_v1_val.json
  │   ├── train2017
  │   │   ├── 000000004134.png
  │   │   ├── 000000031817.png
  │   │   ├── ......
  │   ├── val2017
  │   ├── test2017
  ├── cityscapes
  |   ├── annotations
  │   │   │   ├── instancesonly_filtered_gtFine_train.json
  │   │   │   ├── instancesonly_filtered_gtFine_val.json
  │   ├── leftImg8bit
  │   |   ├── train
  │   │   ├── val
  │   │   ├── test

Note: We used the lvis-v1.0 dataset which consists of 1203 categories.

Training

./scripts/dist_train.sh ./configs/refinemask/coco/r50-refinemask-1x.py 8

Note: The codes only support batch size 1 per GPU, and we trained all models with a total batch size 16x1. If you train models with a total batch size 8x1, the performance may drop. We will support batch size 2 or more per GPU later. You can use ./scripts/slurm_train.sh for training with multi-nodes.

Inference

./scripts/dist_test.sh ./configs/refinemask/coco/r50-refinemask-1x.py xxxx.pth 8

Citation

@article{zhang2021refinemask,
  title={RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features},
  author={Gang, Zhang and Xin, Lu and Jingru, Tan and Jianmin, Li and Zhaoxiang, Zhang and Quanquan, Li and Xiaolin, Hu},
  journal={arXiv preprint arXiv:2104.08569},
  year={2021}
}

RefineMask (CVPR 2021)

Related tags

Overview

RefineMask: Towards High-Quality Instance Segmentation
with Fine-Grained Features (CVPR 2021)

Framework

Main Results

Results on COCO

Results on LVIS

Results on Cityscapes

Efficiency of RefineMask

Usage

Requirements

Datasets

Training

Inference

Citation

Owner

Gang Zhang

an implementation of softmax splatting for differentiable forward warping using PyTorch

The official implementation of CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark

Python library for science observations from the James Webb Space Telescope

Offical implementation of Shunted Self-Attention via Multi-Scale Token Aggregation

A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.

Code for reproducible experiments presented in KSD Aggregated Goodness-of-fit Test.

Official implementation of NeurIPS 2021 paper "One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective"

DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

Multistream CNN for Robust Acoustic Modeling

AI-UPV at IberLEF-2021 EXIST task: Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models

Code for 'Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning' (AAAI 2022)

Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Source code for the Paper: CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints}

DIRL: Domain-Invariant Representation Learning

Aesara is a Python library that allows one to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.

Node Editor Plug for Blender

Code for Mining the Benefits of Two-stage and One-stage HOI Detection

An Official Repo of CVPR '20 "MSeg: A Composite Dataset for Multi-Domain Segmentation"

Cross-platform CLI tool to generate your Github profile's stats and summary.

RefineMask (CVPR 2021)

Related tags

Overview

RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features (CVPR 2021)

Framework

Main Results

Results on COCO

Results on LVIS

Results on Cityscapes

Efficiency of RefineMask

Usage

Requirements

Datasets

Training

Inference

Citation

Owner

Gang Zhang

an implementation of softmax splatting for differentiable forward warping using PyTorch

The official implementation of CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark

Python library for science observations from the James Webb Space Telescope

Offical implementation of Shunted Self-Attention via Multi-Scale Token Aggregation

A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.

Code for reproducible experiments presented in KSD Aggregated Goodness-of-fit Test.

Official implementation of NeurIPS 2021 paper "One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective"

DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

Multistream CNN for Robust Acoustic Modeling

AI-UPV at IberLEF-2021 EXIST task: Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models

Code for 'Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning' (AAAI 2022)

Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Source code for the Paper: CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints}

DIRL: Domain-Invariant Representation Learning

Aesara is a Python library that allows one to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.

Node Editor Plug for Blender

Code for Mining the Benefits of Two-stage and One-stage HOI Detection

An Official Repo of CVPR '20 "MSeg: A Composite Dataset for Multi-Domain Segmentation"

Cross-platform CLI tool to generate your Github profile's stats and summary.

RefineMask: Towards High-Quality Instance Segmentation
with Fine-Grained Features (CVPR 2021)