\u5f53\u7814\u7a76\u5ba4\u306e\u8ad6\u6587\u304cIEICE Trans. Information and Systems\u306b\u63a1\u9332\u3055\u308c\u307e\u3057\u305f\uff0e<\/p>\n\n\n\n
R. Higashimoto, T. Horihata, S. Yoshida, M. Muneyasu: Unbiased Pseudo-Labeling for Learning with Noisy Labels<\/p>\n\n\n\n
\u6982\u8981<\/strong><\/p>\n\n\n\n Noisy labels in training data can significantly harm the performance of deep neural networks (DNNs). Recent research on learning with noisy labels uses a property of DNNs called the memorization effect to divide the training data into a set of data with reliable labels and a set of data with unreliable labels. Methods introducing semi-supervised learning strategies discard the unreliable labels and assign pseudo-labels generated from the confident predictions of the model. So far, this semi-supervised strategy has yielded the best results in this field. However, we observe that even when models are trained on balanced data, the distribution of pseudo-labels can still exhibit imbalance, driven by similarity among data. Additionally, a data bias is seen, originating from the division of training data using the semi-supervised method. If we address these biases that arises from pseudo-labels, we can avoid the decrease in generalization performance caused by biased noisy pseudo-labels. We propose a learning method with noisy labels that introduces unbiased pseudo-labeling based on causal inference. The proposed method achieves significant accuracy gains in experiments at high noise rates on the standard benchmarks CIFAR-10 and CIFAR-100.<\/p>\n","protected":false},"excerpt":{"rendered":" \u5f53\u7814\u7a76\u5ba4\u306e\u8ad6\u6587\u304cIEICE Trans. Information and Systems\u306b\u63a1\u9332\u3055\u308c\u307e\u3057\u305f\uff0e R. Higashimoto, T. Horihata, S. Yoshida, M. Muneyasu: Un […]<\/p>\n","protected":false},"author":285,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[3],"tags":[],"class_list":["post-605","post","type-post","status-publish","format-standard","hentry","category-publications"],"_links":{"self":[{"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/posts\/605","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/users\/285"}],"replies":[{"embeddable":true,"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/comments?post=605"}],"version-history":[{"count":2,"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/posts\/605\/revisions"}],"predecessor-version":[{"id":607,"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/posts\/605\/revisions\/607"}],"wp:attachment":[{"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/media?parent=605"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/categories?post=605"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wps.itc.kansai-u.ac.jp\/s-yos\/wp-json\/wp\/v2\/tags?post=605"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}