{"id":134447,"date":"2022-10-25T19:44:04","date_gmt":"2022-10-25T10:44:04","guid":{"rendered":"http:\/\/192.249.19.202\/?post_type=research-achieve&#038;p=134447"},"modified":"2026-04-13T19:19:45","modified_gmt":"2026-04-13T10:19:45","slug":"prof-sung-ju-lee-and-prof-jinwoo-shin-developed-an-new-ai-technology-and-present-upcoming-neurips-2022","status":"publish","type":"research-achieve","link":"http:\/\/ee.presscat.kr\/en\/research-achieve\/prof-sung-ju-lee-and-prof-jinwoo-shin-developed-an-new-ai-technology-and-present-upcoming-neurips-2022\/","title":{"rendered":"Prof. Sung-Ju Lee and Prof. Jinwoo Shin developed an new AI technology and present upcoming NeurIPS 2022"},"content":{"rendered":"<p><span style=\"font-family: verdana, geneva, sans-serif;color: #000000\"><img fetchpriority=\"high\" decoding=\"async\" class=\"alignnone size-full wp-image-134443\" src=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/10\/\uc5f0\uad6c\uc9c4\uc0ac\uc9c4_\ucea1\ucc98-3.jpg\" alt=\"\" width=\"864\" height=\"151\" title=\"\" srcset=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/10\/\uc5f0\uad6c\uc9c4\uc0ac\uc9c4_\ucea1\ucc98-3.jpg 864w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/10\/\uc5f0\uad6c\uc9c4\uc0ac\uc9c4_\ucea1\ucc98-3-300x52.jpg 300w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/10\/\uc5f0\uad6c\uc9c4\uc0ac\uc9c4_\ucea1\ucc98-3-768x134.jpg 768w\" sizes=\"(max-width: 864px) 100vw, 864px\" \/><\/span><\/p>\n<div class=\"dooray_mail_8550620826875729920\">\n<div dir=\"ltr\">\n<div><span style=\"font-family: verdana, geneva, sans-serif;color: #000000\">[Prof. Sung-Ju Lee, Prof. Jinwoo Shin, Taesik Gong, Jongheon Jeong,\u00a0Yewon Kim ,Taewon Kim, from left]<\/span><\/div>\n<div>\u00a0<\/div>\n<div><span style=\"font-family: verdana, geneva, sans-serif;color: #000000\">A research team led by Professor Sung-Ju Lee of the School of Electrical and Electronic Engineering and Professor Jinwoo Shin of the Graduate School of AI developed a test-time adaptation artificial intelligence technology that adapts itself to environmental changes.\u00a0<\/span><\/div>\n<div><span style=\"font-family: verdana, geneva, sans-serif;color: #000000\">The algorithm proposed by the research team showed an average improvement of 11%\u00a0in accuracy compared to the existing best performing algorithm.<\/span><\/div>\n<div>\u00a0<\/div>\n<div><span style=\"font-family: verdana, geneva, sans-serif;color: #000000\">Titled \u201cNOTE: Robust Continual Test-time Adaptation Against Temporal Correlation,\u201d this study will be presented in December at &#8216;NeurIPS (NeurIPS) 2022&#8217;, one of the most prestigious international conferences in the field of artificial intelligence.<\/span><\/div>\n<div><span style=\"font-family: verdana, geneva, sans-serif;color: #000000\">Dr. Taeshik Gong led the research as the first author, and Jongheon Jeong, Taewon Kim, and Yewon Kim contributed as co-authors.<\/span><\/div>\n<div>\u00a0<\/div>\n<div><span style=\"font-family: verdana, geneva, sans-serif;color: #000000\">Professor Sung-Ju Lee and Professor Jinwoo Shin said, \u201cTest time domain adaptation is a technology that allows artificial intelligence to adapt itself to changes in the environment and improve its performance, and its uses are limitless. The NOTE technology to be announced is the first technology to show performance improvement in actual data distribution, and is expected to be applicable to various fields such as autonomous driving, artificial intelligence medical care, and mobile health care.\u201d<\/span><\/div>\n<div>\u00a0<\/div>\n<\/div>\n<div><span style=\"font-family: verdana, geneva, sans-serif;color: #000000\"><img decoding=\"async\" class=\"alignnone size-full wp-image-134445\" src=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/10\/dataURItoBlob-2.jpg\" alt=\"\" width=\"1000\" height=\"265\" title=\"\" srcset=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/10\/dataURItoBlob-2.jpg 1000w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/10\/dataURItoBlob-2-300x80.jpg 300w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/10\/dataURItoBlob-2-768x204.jpg 768w\" sizes=\"(max-width: 1000px) 100vw, 1000px\" \/><\/span><\/div>\n<div dir=\"ltr\">\n<div>\u00a0<\/div>\n<div><span style=\"font-family: verdana, geneva, sans-serif;color: #000000\">This research was conducted at the Korea Advanced Institute of Science and Technology&#8217;s Future Defense Artificial Intelligence Specialized Research Center (UD190031RD) with support from the National Research Foundation (No. NRF-2020R1A2C1004062).<\/span><\/div>\n<\/div>\n<\/div>\n<div>\u00a0<\/div>\n","protected":false},"excerpt":{"rendered":"<p>731<\/p>\n","protected":false},"featured_media":134445,"template":"","research_category":[],"class_list":["post-134447","research-achieve","type-research-achieve","status-publish","has-post-thumbnail","hentry"],"acf":[],"_links":{"self":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research-achieve\/134447","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research-achieve"}],"about":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/types\/research-achieve"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media\/134445"}],"wp:attachment":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media?parent=134447"}],"wp:term":[{"taxonomy":"research_category","embeddable":true,"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research_category?post=134447"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}