{"title":"用于半监督语义分割的类概率空间正规化","authors":"","doi":"10.1016/j.cviu.2024.104146","DOIUrl":null,"url":null,"abstract":"<div><p>Semantic segmentation achieves fine-grained scene parsing in any scenario, making it one of the key research directions to facilitate the development of human visual attention mechanisms. Recent advancements in semi-supervised semantic segmentation have attracted considerable attention due to their potential in leveraging unlabeled data. However, existing methods only focus on exploring the knowledge of unlabeled pixels with high certainty prediction. Their insufficient mining of low certainty regions of unlabeled data results in a significant loss of supervisory information. Therefore, this paper proposes the <strong>C</strong>lass <strong>P</strong>robability <strong>S</strong>pace <strong>R</strong>egularization (<strong>CPSR</strong>) approach to further exploit the potential of each unlabeled pixel. Specifically, we first design a class knowledge reshaping module to regularize the probability space of low certainty pixels, thereby transforming them into high certainty ones for supervised training. Furthermore, we propose a tail probability suppression module to suppress the probabilities of tailed classes, which facilitates the network to learn more discriminative information from the class probability space. Extensive experiments conducted on the PASCAL VOC2012 and Cityscapes datasets prove that our method achieves state-of-the-art performance without introducing much computational overhead. Code is available at <span><span>https://github.com/MKSAQW/CPSR</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Class Probability Space Regularization for semi-supervised semantic segmentation\",\"authors\":\"\",\"doi\":\"10.1016/j.cviu.2024.104146\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Semantic segmentation achieves fine-grained scene parsing in any scenario, making it one of the key research directions to facilitate the development of human visual attention mechanisms. Recent advancements in semi-supervised semantic segmentation have attracted considerable attention due to their potential in leveraging unlabeled data. However, existing methods only focus on exploring the knowledge of unlabeled pixels with high certainty prediction. Their insufficient mining of low certainty regions of unlabeled data results in a significant loss of supervisory information. Therefore, this paper proposes the <strong>C</strong>lass <strong>P</strong>robability <strong>S</strong>pace <strong>R</strong>egularization (<strong>CPSR</strong>) approach to further exploit the potential of each unlabeled pixel. Specifically, we first design a class knowledge reshaping module to regularize the probability space of low certainty pixels, thereby transforming them into high certainty ones for supervised training. Furthermore, we propose a tail probability suppression module to suppress the probabilities of tailed classes, which facilitates the network to learn more discriminative information from the class probability space. Extensive experiments conducted on the PASCAL VOC2012 and Cityscapes datasets prove that our method achieves state-of-the-art performance without introducing much computational overhead. Code is available at <span><span>https://github.com/MKSAQW/CPSR</span><svg><path></path></svg></span>.</p></div>\",\"PeriodicalId\":50633,\"journal\":{\"name\":\"Computer Vision and Image Understanding\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-09-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Vision and Image Understanding\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1077314224002273\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224002273","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
Class Probability Space Regularization for semi-supervised semantic segmentation
Semantic segmentation achieves fine-grained scene parsing in any scenario, making it one of the key research directions to facilitate the development of human visual attention mechanisms. Recent advancements in semi-supervised semantic segmentation have attracted considerable attention due to their potential in leveraging unlabeled data. However, existing methods only focus on exploring the knowledge of unlabeled pixels with high certainty prediction. Their insufficient mining of low certainty regions of unlabeled data results in a significant loss of supervisory information. Therefore, this paper proposes the Class Probability Space Regularization (CPSR) approach to further exploit the potential of each unlabeled pixel. Specifically, we first design a class knowledge reshaping module to regularize the probability space of low certainty pixels, thereby transforming them into high certainty ones for supervised training. Furthermore, we propose a tail probability suppression module to suppress the probabilities of tailed classes, which facilitates the network to learn more discriminative information from the class probability space. Extensive experiments conducted on the PASCAL VOC2012 and Cityscapes datasets prove that our method achieves state-of-the-art performance without introducing much computational overhead. Code is available at https://github.com/MKSAQW/CPSR.
期刊介绍:
The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views.
Research Areas Include:
• Theory
• Early vision
• Data structures and representations
• Shape
• Range
• Motion
• Matching and recognition
• Architecture and languages
• Vision systems