Data

Tools

Indexes

Applications

Experiments

Open Source Science

light4mars

code implement of our paper: a Lightweight Transformer Model for Semantic Segmentation on Unstructured Environment like Mars

https://github.com/cvir-lab/light4mars

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.3%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

code implement of our paper: a Lightweight Transformer Model for Semantic Segmentation on Unstructured Environment like Mars

Basic Info
  • Host: GitHub
  • Owner: CVIR-Lab
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 72.3 KB
Statistics
  • Stars: 13
  • Watchers: 0
  • Forks: 2
  • Open Issues: 1
  • Releases: 0
Created over 2 years ago · Last pushed 10 months ago
Metadata Files
Readme License Citation

README.md

Light4Mars：A Lightweight Transformer Model for Semantic Segmentation on Unstructured Environment Like Mars

Introduction

This repository is the code implementation of the paper Light4Mars：A Lightweight Transformer Model for Semantic Segmentation on Unstructured Environment Like Mars, which is based on the MMSegmentation project.

Installation

Step 0: Create a virtual environment named light4mars and activate it. conda create -n light4mars python=3.8 -y conda activate light4mars

Step 1: Install PyTorch 2.0.1 and torchvision 0.15.2. pip install torch==2.0.1 pip install torchvision==0.15.2

Step 2: Install MMCV and mmsegmentation. pip install -U openmim mim install mmengine==0.8.4 mim install mmcv=2.0.0 pip install mmsegmentation=1.1.1

Dataset Preparation

The dataset used in the paper is called SynMars-TW, which is an open source unstructured environmental fine-grained synthetic dataset based on real data from the TianWen-1 mission. Please download the SynMars-TW dataset and set it according to the MMSegmentation data format.

Model Training

python train.py configs/light4mars/light4mars-b_synmars-tw.py

Model Testing

python test.py configs/light4mars/light4mars-b_synmars-tw.py

Citation

If you use the code or performance benchmarks of this project in your research, please refer to the following bibtex citation of Light4Mars. @article{xiong2024light4mars, title={Light4Mars: A lightweight transformer model for semantic segmentation on unstructured environment like Mars}, author={Xiong, Yonggang and Xiao, Xueming and Yao, Meibao and Cui, Hutao and Fu, Yuegang}, journal={ISPRS Journal of Photogrammetry and Remote Sensing}, volume={214}, pages={167--178}, year={2024}, publisher={Elsevier} }

Owner

  • Name: CVIR-Lab
  • Login: CVIR-Lab
  • Kind: organization

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMSegmentation Contributors"
title: "OpenMMLab Semantic Segmentation Toolbox and Benchmark"
date-released: 2020-07-10
url: "https://github.com/open-mmlab/mmsegmentation"
license: Apache-2.0

GitHub Events

Total
  • Watch event: 2
  • Issue comment event: 1
  • Push event: 26
  • Fork event: 1
Last Year
  • Watch event: 2
  • Issue comment event: 1
  • Push event: 26
  • Fork event: 1