• Stars
    star
    224
  • Rank 177,792 (Top 4 %)
  • Language
    Python
  • License
    MIT License
  • Created over 4 years ago
  • Updated over 3 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

CVPR2020, Multi-scale Interactive Network for Salient Object Detection

Multi-scale Interactive Network for Salient Object Detection

License: MIT GitHub last commit GitHub issues GitHub stars CVPR Page Arxiv Page

CVPR 2020.

NONE: For subsequent updates of the paper, please see the arixv version.

Changelog

The code and experimental results have be released now 😄.

  • 2021/6/6:
    • Move the script cal_fps.py into the folder tools.
    • Add a script in tools folder for the model inference on your own datasets.
    • Improve code/readme.md.
  • 2021/1/18:
    • Fix the form of the SIM module: #15
  • 2020/12/08:
    • Simplify the code structure.
    • Add a simple version to the simpler branch, but I have no time to test it. So, if you find any bugs, you can create an issue.
    • Add the pre-commit hook to format the code before the commit.
  • 2020/7/23:
    • Improve and simplify the configuration of the project.
    • Introduce the support of Amp: Automatic Mixed Precision. (Quick Start)
    • Confirm the correctness of the function of saving and resuming the checkpoint.
      • The training was interrupted.
      • Training from scratch.
      • Test only.
    • Confirm the correctness of the function of exporting xlsx.
  • 2020/7/16:
    • Fix the mistake pointed out by @sjf18 in our code for testing FPS, which will be corrected in the later version of the paper.
  • 2020/7/14:
    • The actual interpolation method is pointed out.
    • Modify the mode of F.interpolate in SIM from scale_factor to size.
  • 2020/6/21: Some useful modifications.
    • I optimized the testing process. For details, you can see code/readme.md.
    • Added some backbone models using ws+gn which can further improve the generalization performance of the model. If there is a need, I can provide the pretrained parameter file of the corresponding improved version of MINet. :)
    • The directory structure has been adjusted.
  • 2020/5/10: Some meaningful changes.
    • Some methods have been tried to improve the performance of the model on specific operating environments and devices. The specific experimental results can be found in the section "More Experiments" of ./code/readme.md.
    • Use black as the repository formatting tool, and set the configuration file ./code/pyproject.toml.
  • 2020/5/6: Add some new attempts and improvements.
    • Modified the method of importing model from the directly setting in config.py, and change it to the automatic selection and instantiation of the specific model class according to the model alias (exp_name in config.py).
    • Added a lighter setting for AIM and MInet.
    • Added an attempt to checkpoint features of PyTorch.
    • Added learning rate decay strategy with learning rate warm-up. However, the parameter setting is not flexible at present, and needs to be improved.
    • A new optimization strategy has been added to imitate the settings from F3Net.
    • Upload the MIT LICENSE file.
  • 2020/4/16: Modify some misleading descriptions in the readme.md file.
  • 2020/4/7: Simplify the structure of the repository.
  • 2020/3/29: Update the method of evaluating results. (See the readme.md for more details.)
  • 2020/3/28: Update our code, results, pretrained parameters and some documents.

Repository Details

  • code: Complete training and testing code about our method. The readme.md file describes how to use the code.
  • docs: Github page about out paper. Here are some paper details.

Related Links

Paper Details

Abstract

Deep-learning based salient object detection methods achieve great progress. However, the variable scale and unknown category of salient objects are great challenges all the time. These are closely related to the utilization of multi-level and multi-scale features. In this paper, we propose the aggregate interaction modules to integrate the features from adjacent levels, in which less noise is introduced because of only using small up-/down-sampling rates. To obtain more efficient multi-scale features from the integrated features, the self-interaction modules are embedded in each decoder unit. Besides, the class imbalance issue caused by the scale variation weakens the effect of the binary cross entropy loss and results in the spatial inconsistency of the predictions. Therefore, we exploit the consistency-enhanced loss to highlight the fore-/back-ground difference and preserve the intra-class consistency. Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches. The source code will be publicly available at https://github.com/lartpang/MINet.

Architecture

Comparison

BibTeX

@inproceedings{MINet-CVPR2020,
    author = {Pang, Youwei and Zhao, Xiaoqi and Zhang, Lihe and Lu, Huchuan},
    title = {Multi-Scale Interactive Network for Salient Object Detection},
    booktitle = CVPR,
    month = {June},
    year = {2020}
}

More Repositories

1

PyTorchTricks

Some tricks of pytorch... ⭐
1,036
star
2

awesome-segmentation-saliency-dataset

A collection of some datasets for segmentation / saliency detection. Welcome to PR...😄
475
star
3

Machine-Deep-Learning

👋 ML/DL学习笔记(基础+论文)
218
star
4

PySODEvalToolkit

PySODEvalToolkit: A Python-based Evaluation Toolbox for Salient Object Detection and Camouflaged Object Detection
Python
110
star
5

ZoomNet

Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection, CVPR 2022
Python
100
star
6

PySODMetrics

PySODMetrics: A Simple and Efficient Implementation of Grayscale/Binary Segmentation Metrcis
Python
82
star
7

HDFNet

(ECCV 2020) Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection
Python
78
star
8

spyder_tool

💥 常用有效、给力的pyhton爬虫工具集合,欢迎PR,共同建设,目前不怎么做爬虫了,有朋友愿意更新的可以发PR。
62
star
9

PyTorchCoding

Some example of PyTorch about some papers
Python
18
star
10

CAVER

CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
Python
11
star
11

MSSIM.pytorch

A better pytorch-based implementation for the mean structural similarity. Differentiable simpler SSIM and MS-SSIM.
Python
11
star
12

LinuxNote

🐧 Store some notes about linux.
10
star
13

RunIt

A simple program scheduler for your code on different devices.
Python
10
star
14

MethodsCmp

MethodsCmp: A Simple Toolkit for Counting the FLOPs/MACs, Parameters and FPS of Pytorch-based Methods
Python
9
star
15

CodeForArticle

Code For My Articles
Python
7
star
16

ManageMyAttachments

Some useful tools to help manage attachments in my local markdown projects.
Go
5
star
17

OpticalFlowBasedVOS

A simple and efficient codebase for the optical flow based video object segmentation.
Python
5
star
18

MyCoding

some projects for learing coding.
Jupyter Notebook
4
star
19

RegisterIt

A more flexible register for the DeepLearning project.
Python
4
star
20

SynsetsTools

A toolkit for the site <https://synsets.net> that consults synonyms and antonyms and it will continue to be updated later.
Python
4
star
21

myoptions

🐬 集中存放一些配置文件 vim/zsh/ublock origin/...
Vim Script
4
star
22

CMWNet.pytorch

This project provides an unofficial pytorch implementation of the RGB-D SOD method for 'Cross-Modal Weighting Network for RGB-D Salient Object Detection', ECCV 2020.
Python
3
star
23

cs231n-forme-2018

cs231n
Jupyter Notebook
3
star
24

blog

A personal blog using GitHub Issues and GitHub Actions based on https://github.com/yihong0618/gitblog.
Python
3
star
25

PyDavis16EvalToolbox

A Python-based video object segmentation evaluation toolbox.
Python
3
star
26

Distributed-SOD-Project

Some attempts to use distributed and mixed precision (pytorch, apex) to train salient object detection models
Python
3
star
27

LaTeXNote

some notes about using LaTeX.
2
star
28

CoSaliencyProj

A project for co-saliency detection. Some codes are borrowed from ICNet. Thanks to ICNet Intra-saliency Correlation Network for Co-Saliency Detection (NIPS2020)~
Python
2
star
29

AutoUpdateConfiguration

Some configuration files updated by GitHub Actions.
Python
2
star
30

PyLoss

Some loss functions for deeplearning.
Python
2
star
31

YuQueTools

用于语雀的小工具
Python
2
star
32

lartpang.github.io

Personal homepage.
HTML
2
star
33

lartpang

My Life
Python
2
star
34

PaperList

My Collection of Papers.
2
star
35

PySODToolBox

A toolbox for salient object detection.
Python
1
star
36

TerminalPainter

Draw pictures or videos on the terminal.
Python
1
star
37

mymatlab

some matlab files
HTML
1
star
38

ClusteringMethods

Some Clustering Methods Implementation Base on Python.
Jupyter Notebook
1
star
39

PySchedule

A small deadline countdown tool, but it is still in the stage of the command line interface.
Python
1
star
40

Validation

The code snippet used for validation.
1
star
41

Hands-on-Docker

一份详尽的Docker使用指南
1
star
42

DL-Utils

Some tools for deeplearning works.
Python
1
star
43

somethings

平时做的一些小项目
C
1
star
44

PaperCollection

A collection of important papers for different views.
1
star
45

AllinLosses

Deep learning of all loss functions
Python
1
star
46

awesome-class-activation-map

An awesome list of papers and tools about the class activation map (CAM) technology.
1
star