A Novel Shape Guided Transformer Network for Instance Segmentation in Remote Sensing Images
December 31, 2024 ยท Entered Twilight ยท ๐ IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
"Paper promises code 'coming soon'"
"Code repo scraped from project page (backfill)"
Evidence collected by the PWNC Scanner
Repo contents: LovaszSoftmaxloss.py, README.md, SLCNet.py, __init__.py, predict_model.py, tools.py, train_model.py
Authors
Dawen Yu, Shunping Ji
arXiv ID
2501.00360
Category
cs.CV: Computer Vision
Cross-listed
cs.LG
Citations
5
Venue
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Repository
https://github.com/yudawen/SLCNet
โญ 8
Last Checked
2 months ago
Abstract
Instance segmentation performance in remote sensing images (RSIs) is significantly affected by two issues: how to extract accurate boundaries of objects from remote imaging through the dynamic atmosphere, and how to integrate the mutual information of related object instances scattered over a vast spatial region. In this study, we propose a novel Shape Guided Transformer Network (SGTN) to accurately extract objects at the instance level. Inspired by the global contextual modeling capacity of the self-attention mechanism, we propose an effective transformer encoder termed LSwin, which incorporates vertical and horizontal 1D global self-attention mechanisms to obtain better global-perception capacity for RSIs than the popular local-shifted-window based Swin Transformer. To achieve accurate instance mask segmentation, we introduce a shape guidance module (SGM) to emphasize the object boundary and shape information. The combination of SGM, which emphasizes the local detail information, and LSwin, which focuses on the global context relationships, achieve excellent RSI instance segmentation. Their effectiveness was validated through comprehensive ablation experiments. Especially, LSwin is proved better than the popular ResNet and Swin transformer encoder at the same level of efficiency. Compared to other instance segmentation methods, our SGTN achieves the highest average precision (AP) scores on two single-class public datasets (WHU dataset and BITCC dataset) and a multi-class public dataset (NWPU VHR-10 dataset). Code will be available at http://gpcv.whu.edu.cn/data/.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computer Vision
๐
๐
Old Age
๐
๐
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
๐
๐
Old Age
SSD: Single Shot MultiBox Detector
๐
๐
Old Age
Squeeze-and-Excitation Networks
๐
๐
Old Age
Fast R-CNN
๐
๐
Old Age