Physically-guided open vocabulary segmentation with weighted patched alignment loss

IF 5.5 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Weide Liu , Jieming Lou , Xingxing Wang , Wei Zhou , Jun Cheng , Xulei Yang
{"title":"Physically-guided open vocabulary segmentation with weighted patched alignment loss","authors":"Weide Liu ,&nbsp;Jieming Lou ,&nbsp;Xingxing Wang ,&nbsp;Wei Zhou ,&nbsp;Jun Cheng ,&nbsp;Xulei Yang","doi":"10.1016/j.neucom.2024.128788","DOIUrl":null,"url":null,"abstract":"<div><div>Open vocabulary segmentation is a challenging task that aims to segment out the thousands of unseen categories. Directly applying CLIP to open-vocabulary semantic segmentation is challenging due to the granularity gap between its image-level contrastive learning and the pixel-level recognition required for segmentation. To address these challenges, we propose a unified pipeline that leverages physical structure regularization to enhance the generalizability and robustness of open vocabulary segmentation. By incorporating physical structure information, which is independent of the training data, we aim to reduce bias and improve the model’s performance on unseen classes. We utilize low-level structures such as edges and keypoints as regularization terms, as they are easier to obtain and strongly correlated with segmentation boundary information. These structures are used as pseudo-ground truth to supervise the model. Furthermore, inspired by the effectiveness of comparative learning in human cognition, we introduce the weighted patched alignment loss. This loss function contrasts similar and dissimilar samples to acquire low-dimensional representations that capture the distinctions between different object classes. By incorporating physical knowledge and leveraging weighted patched alignment loss, we aim to improve the model’s generalizability, robustness, and capability to recognize diverse object classes. The experiments on the COCO Stuff, Pascal VOC, Pascal Context-59, Pascal Context-459, ADE20K-150, and ADE20K-847 datasets demonstrate that our proposed method consistently improves baselines and achieves new state-of-the-art in the open vocabulary segmentation task.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"614 ","pages":"Article 128788"},"PeriodicalIF":5.5000,"publicationDate":"2024-10-28","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/S0925231224015595","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

Open vocabulary segmentation is a challenging task that aims to segment out the thousands of unseen categories. Directly applying CLIP to open-vocabulary semantic segmentation is challenging due to the granularity gap between its image-level contrastive learning and the pixel-level recognition required for segmentation. To address these challenges, we propose a unified pipeline that leverages physical structure regularization to enhance the generalizability and robustness of open vocabulary segmentation. By incorporating physical structure information, which is independent of the training data, we aim to reduce bias and improve the model’s performance on unseen classes. We utilize low-level structures such as edges and keypoints as regularization terms, as they are easier to obtain and strongly correlated with segmentation boundary information. These structures are used as pseudo-ground truth to supervise the model. Furthermore, inspired by the effectiveness of comparative learning in human cognition, we introduce the weighted patched alignment loss. This loss function contrasts similar and dissimilar samples to acquire low-dimensional representations that capture the distinctions between different object classes. By incorporating physical knowledge and leveraging weighted patched alignment loss, we aim to improve the model’s generalizability, robustness, and capability to recognize diverse object classes. The experiments on the COCO Stuff, Pascal VOC, Pascal Context-59, Pascal Context-459, ADE20K-150, and ADE20K-847 datasets demonstrate that our proposed method consistently improves baselines and achieves new state-of-the-art in the open vocabulary segmentation task.
利用加权修补对齐损失进行物理引导的开放词汇分割
开放词汇分割是一项具有挑战性的任务,其目的是分割出数千个未见类别。将 CLIP 直接应用于开放词汇语义分割具有挑战性,因为其图像级对比学习与分割所需的像素级识别之间存在粒度差距。为了应对这些挑战,我们提出了一个统一的管道,利用物理结构正则化来增强开放词汇分割的通用性和鲁棒性。通过纳入独立于训练数据的物理结构信息,我们旨在减少偏差并提高模型在未见类别上的性能。我们利用边缘和关键点等低级结构作为正则化条件,因为它们更容易获得,而且与分割边界信息密切相关。这些结构被用作监督模型的伪地面真实信息。此外,受人类认知中比较学习有效性的启发,我们引入了加权修补对齐损失。该损失函数对相似样本和不相似样本进行对比,从而获得低维表征,捕捉不同物体类别之间的区别。通过结合物理知识和利用加权修补配准损失,我们旨在提高模型的通用性、鲁棒性和识别不同物体类别的能力。在 COCO Stuff、Pascal VOC、Pascal Context-59、Pascal Context-459、ADE20K-150 和 ADE20K-847 数据集上的实验表明,我们提出的方法在开放词汇分割任务中不断改进基线并达到新的一流水平。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
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.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信