SARFormer: Segmenting Anything Guided Transformer for semantic segmentation

IF 5.5 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Neurocomputing Pub Date : 2025-03-14 DOI:10.1016/j.neucom.2025.129915
Lixin Zhang , Wenteng Huang , Bin Fan
{"title":"SARFormer: Segmenting Anything Guided Transformer for semantic segmentation","authors":"Lixin Zhang ,&nbsp;Wenteng Huang ,&nbsp;Bin Fan","doi":"10.1016/j.neucom.2025.129915","DOIUrl":null,"url":null,"abstract":"<div><div>Semantic segmentation plays a crucial role in robotic systems. Despite advances, we find that current state-of-the-art methods are hard to apply in practice due to their weak generalization ability. Especially, diffusion-based segmentation methods struggle with over-reliance on noisy Ground Truth (GT) annotations, which are corrupted with noise and directly fed into the model’s forward propagation process during training, limiting the model’s ability to generalize. While the Segment Anything Model (SAM) excels at instance segmentation, it faces challenges in controlling granularity and lacks semantic information. To address these issues, we propose SARFormer, a semantic segmentation algorithm guided by SAM. Unlike conventional methods, SARFormer uses GT solely for supervision and replaces noisy GT with SAM guidance, enabling better generalization. The key innovations include a region-based SAM optimizer to refine granularity and a feature aggregation method for enhanced deep feature extraction. Experimental results show SARFormer achieves competitive accuracy, demonstrating the effectiveness of SAM in improving segmentation performance</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"635 ","pages":"Article 129915"},"PeriodicalIF":5.5000,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurocomputing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0925231225005879","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Semantic segmentation plays a crucial role in robotic systems. Despite advances, we find that current state-of-the-art methods are hard to apply in practice due to their weak generalization ability. Especially, diffusion-based segmentation methods struggle with over-reliance on noisy Ground Truth (GT) annotations, which are corrupted with noise and directly fed into the model’s forward propagation process during training, limiting the model’s ability to generalize. While the Segment Anything Model (SAM) excels at instance segmentation, it faces challenges in controlling granularity and lacks semantic information. To address these issues, we propose SARFormer, a semantic segmentation algorithm guided by SAM. Unlike conventional methods, SARFormer uses GT solely for supervision and replaces noisy GT with SAM guidance, enabling better generalization. The key innovations include a region-based SAM optimizer to refine granularity and a feature aggregation method for enhanced deep feature extraction. Experimental results show SARFormer achieves competitive accuracy, demonstrating the effectiveness of SAM in improving segmentation performance
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
来源期刊
Neurocomputing
Neurocomputing 工程技术-计算机:人工智能
CiteScore
13.10
自引率
10.00%
发文量
1382
审稿时长
70 days
期刊介绍: Neurocomputing publishes articles describing recent fundamental contributions in the field of neurocomputing. Neurocomputing theory, practice and applications are the essential topics being covered.
期刊最新文献
Handling language prior and compositional reasoning issues in Visual Question Answering system Reliable ℓ2−ℓ∞ state estimation for delayed neural networks under weighted try-one-discard protocol SARFormer: Segmenting Anything Guided Transformer for semantic segmentation Brain state model: A novel method to represent the rhythmicity of object-specific selective attention from magnetoencephalography data A survey on dynamic scene understanding using temporal knowledge graphs: From scene knowledge representation to extrapolation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1