Xiaohuan Lu, Lian Zhao, Wai Keung Wong, Jie Wen, Jiang Long, Wulin Xie
{"title":"用于部分多视图不完整多标签分类的任务增强型交叉视图估算网络","authors":"Xiaohuan Lu, Lian Zhao, Wai Keung Wong, Jie Wen, Jiang Long, Wulin Xie","doi":"arxiv-2409.07931","DOIUrl":null,"url":null,"abstract":"In real-world scenarios, multi-view multi-label learning often encounters the\nchallenge of incomplete training data due to limitations in data collection and\nunreliable annotation processes. The absence of multi-view features impairs the\ncomprehensive understanding of samples, omitting crucial details essential for\nclassification. To address this issue, we present a task-augmented cross-view\nimputation network (TACVI-Net) for the purpose of handling partial multi-view\nincomplete multi-label classification. Specifically, we employ a two-stage\nnetwork to derive highly task-relevant features to recover the missing views.\nIn the first stage, we leverage the information bottleneck theory to obtain a\ndiscriminative representation of each view by extracting task-relevant\ninformation through a view-specific encoder-classifier architecture. In the\nsecond stage, an autoencoder based multi-view reconstruction network is\nutilized to extract high-level semantic representation of the augmented\nfeatures and recover the missing data, thereby aiding the final classification\ntask. Extensive experiments on five datasets demonstrate that our TACVI-Net\noutperforms other state-of-the-art methods.","PeriodicalId":501130,"journal":{"name":"arXiv - CS - Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Task-Augmented Cross-View Imputation Network for Partial Multi-View Incomplete Multi-Label Classification\",\"authors\":\"Xiaohuan Lu, Lian Zhao, Wai Keung Wong, Jie Wen, Jiang Long, Wulin Xie\",\"doi\":\"arxiv-2409.07931\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In real-world scenarios, multi-view multi-label learning often encounters the\\nchallenge of incomplete training data due to limitations in data collection and\\nunreliable annotation processes. The absence of multi-view features impairs the\\ncomprehensive understanding of samples, omitting crucial details essential for\\nclassification. To address this issue, we present a task-augmented cross-view\\nimputation network (TACVI-Net) for the purpose of handling partial multi-view\\nincomplete multi-label classification. Specifically, we employ a two-stage\\nnetwork to derive highly task-relevant features to recover the missing views.\\nIn the first stage, we leverage the information bottleneck theory to obtain a\\ndiscriminative representation of each view by extracting task-relevant\\ninformation through a view-specific encoder-classifier architecture. In the\\nsecond stage, an autoencoder based multi-view reconstruction network is\\nutilized to extract high-level semantic representation of the augmented\\nfeatures and recover the missing data, thereby aiding the final classification\\ntask. Extensive experiments on five datasets demonstrate that our TACVI-Net\\noutperforms other state-of-the-art methods.\",\"PeriodicalId\":501130,\"journal\":{\"name\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07931\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07931","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Task-Augmented Cross-View Imputation Network for Partial Multi-View Incomplete Multi-Label Classification
In real-world scenarios, multi-view multi-label learning often encounters the
challenge of incomplete training data due to limitations in data collection and
unreliable annotation processes. The absence of multi-view features impairs the
comprehensive understanding of samples, omitting crucial details essential for
classification. To address this issue, we present a task-augmented cross-view
imputation network (TACVI-Net) for the purpose of handling partial multi-view
incomplete multi-label classification. Specifically, we employ a two-stage
network to derive highly task-relevant features to recover the missing views.
In the first stage, we leverage the information bottleneck theory to obtain a
discriminative representation of each view by extracting task-relevant
information through a view-specific encoder-classifier architecture. In the
second stage, an autoencoder based multi-view reconstruction network is
utilized to extract high-level semantic representation of the augmented
features and recover the missing data, thereby aiding the final classification
task. Extensive experiments on five datasets demonstrate that our TACVI-Net
outperforms other state-of-the-art methods.