Yuxuan Luo , Jinpeng Chen , Runmin Cong , Horace Ho Shing Ip , Sam Kwong
{"title":"Trace Back and Go Ahead: Completing partial annotation for continual semantic segmentation","authors":"Yuxuan Luo , Jinpeng Chen , Runmin Cong , Horace Ho Shing Ip , Sam Kwong","doi":"10.1016/j.patcog.2025.111613","DOIUrl":null,"url":null,"abstract":"<div><div>Existing Continual Semantic Segmentation (CSS) methods effectively address the issue of <em>background shift</em> in regular training samples. However, this issue persists in exemplars, <em>i.e.</em>, replay samples, which is often overlooked. Each exemplar is annotated only with the classes from its originating task, while other past classes and the current classes during replay are labeled as <em>background</em>. This partial annotation can erase the network’s knowledge of previous classes and impede the learning of new classes. To resolve this, we introduce a new method named Trace Back and Go Ahead (TAGA), which utilizes a backward annotator model and a forward annotator model to generate pseudo-labels for both regular training samples and exemplars, aiming at reducing the adverse effects of incomplete annotations. This approach effectively mitigates the risk of incorrect guidance from both sample types, offering a comprehensive solution to <em>background shift</em>. Additionally, due to a significantly smaller number of exemplars compared to regular training samples, the class distribution in the sample pool of each incremental task exhibits a long-tailed pattern, potentially biasing classification towards incremental classes. Consequently, TAGA incorporates a class-equilibrium sampling strategy that adaptively adjusts the sampling frequencies based on the ratios of exemplars to regular samples and past to new classes, counteracting the skewed distribution. Extensive experiments on two public datasets, Pascal VOC 2012 and ADE20K, demonstrate that our method surpasses state-of-the-art methods.</div></div>","PeriodicalId":49713,"journal":{"name":"Pattern Recognition","volume":"165 ","pages":"Article 111613"},"PeriodicalIF":7.5000,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pattern Recognition","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0031320325002730","RegionNum":1,"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
Existing Continual Semantic Segmentation (CSS) methods effectively address the issue of background shift in regular training samples. However, this issue persists in exemplars, i.e., replay samples, which is often overlooked. Each exemplar is annotated only with the classes from its originating task, while other past classes and the current classes during replay are labeled as background. This partial annotation can erase the network’s knowledge of previous classes and impede the learning of new classes. To resolve this, we introduce a new method named Trace Back and Go Ahead (TAGA), which utilizes a backward annotator model and a forward annotator model to generate pseudo-labels for both regular training samples and exemplars, aiming at reducing the adverse effects of incomplete annotations. This approach effectively mitigates the risk of incorrect guidance from both sample types, offering a comprehensive solution to background shift. Additionally, due to a significantly smaller number of exemplars compared to regular training samples, the class distribution in the sample pool of each incremental task exhibits a long-tailed pattern, potentially biasing classification towards incremental classes. Consequently, TAGA incorporates a class-equilibrium sampling strategy that adaptively adjusts the sampling frequencies based on the ratios of exemplars to regular samples and past to new classes, counteracting the skewed distribution. Extensive experiments on two public datasets, Pascal VOC 2012 and ADE20K, demonstrate that our method surpasses state-of-the-art methods.
期刊介绍:
The field of Pattern Recognition is both mature and rapidly evolving, playing a crucial role in various related fields such as computer vision, image processing, text analysis, and neural networks. It closely intersects with machine learning and is being applied in emerging areas like biometrics, bioinformatics, multimedia data analysis, and data science. The journal Pattern Recognition, established half a century ago during the early days of computer science, has since grown significantly in scope and influence.