{"id":118524,"date":"2021-11-01T00:26:18","date_gmt":"2021-10-31T15:26:18","guid":{"rendered":"http:\/\/175.125.95.178\/ai-in-signal\/18524\/"},"modified":"2026-04-07T12:26:14","modified_gmt":"2026-04-07T03:26:14","slug":"18524","status":"publish","type":"ai-in-signal","link":"http:\/\/ee.presscat.kr\/en\/ai-in-signal\/18524\/","title":{"rendered":"Joint Negative and Positive Learning for Noisy Labels(CVPR 2021)"},"content":{"rendered":"<p>Youngdong Kim, Juseung Yun, Hyounguk Shon and Junmo Kim<\/p>\n<p>Training of Convolutional Neural Networks (CNNs) with data with noisy labels is known to be a challenge. Based on the fact that directly providing the label to the data (Positive Learning; PL) has a risk of allowing CNNs to memorize the contaminated labels for the case of noisy data, the indirect learning approach that uses complementary labels (Negative Learning for Noisy Labels; NLNL) has proven to be highly effective in preventing overfitting to noisy data as it reduces the risk of providing faulty target. NLNL further employs a three-stage pipeline to improve convergence. As a result, filtering noisy data through the NLNL pipeline is cumbersome, increasing the training cost. In this study, we propose a novel improvement of NLNL, named Joint Negative and Positive Learning (JNPL), that unifies the filtering pipeline into a single stage. JNPL trains CNN via two losses, NL+ and PL+, which are improved upon NL and PL loss functions, respectively. We analyze the fundamental issue of NL loss function and develop new NL+ loss function producing gradient that enhances the convergence of noisy data. Furthermore, PL+ loss function is designed to enable faster convergence to expected-to-be-clean data. We show that the NL+ and PL+ train CNN simultaneously, significantly simplifying the pipeline, allowing greater ease of practical use compared to NLNL. With a simple semi-supervised training technique, our method achieves state-of-the-art accuracy for noisy data classification based on the superior filtering ability.<br \/>\n&nbsp;<\/p>\n<p><div class=\"\"><img decoding=\"async\" class=\"\" src=\"\/wp-content\/uploads\/drupal\/\uae40\uc900\ubaa8\uad50\uc218\ub2d812.png\" alt=\"\" title=\"\"><\/div>\n<\/p>\n<p><div class=\"\"><img decoding=\"async\" class=\"\" src=\"\/wp-content\/uploads\/drupal\/\uae40\uc900\ubaa8\uad50\uc218\ub2d813.png\" alt=\"\" title=\"\"><\/div><\/p>\n","protected":false},"excerpt":{"rendered":"<p>746<\/p>\n","protected":false},"featured_media":0,"template":"","class_list":["post-118524","ai-in-signal","type-ai-in-signal","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/ai-in-signal\/118524","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/ai-in-signal"}],"about":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/types\/ai-in-signal"}],"wp:attachment":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media?parent=118524"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}