{"id":1179,"date":"2021-12-16T13:35:00","date_gmt":"2021-12-16T04:35:00","guid":{"rendered":"https:\/\/kakaoenterprise.com\/?post_type=about&p=1179"},"modified":"2022-07-27T14:21:29","modified_gmt":"2022-07-27T05:21:29","slug":"%ec%b9%b4%ec%b9%b4%ec%98%a4%ec%97%94%ed%84%b0%ed%94%84%eb%9d%bc%ec%9d%b4%ec%a6%88-%ea%b8%80%eb%a1%9c%eb%b2%8c-%ec%b5%9c%ea%b3%a0-ai-%ed%95%99%ed%9a%8c-%eb%89%b4%eb%a6%bd%ec%8a%a4neurlps-2021","status":"publish","type":"about","link":"https:\/\/kakaoenterprise.com\/about\/%ec%b9%b4%ec%b9%b4%ec%98%a4%ec%97%94%ed%84%b0%ed%94%84%eb%9d%bc%ec%9d%b4%ec%a6%88-%ea%b8%80%eb%a1%9c%eb%b2%8c-%ec%b5%9c%ea%b3%a0-ai-%ed%95%99%ed%9a%8c-%eb%89%b4%eb%a6%bd%ec%8a%a4neurlps-2021\/","title":{"rendered":"\uae00\ub85c\ubc8c \ucd5c\uace0 AI \ud559\ud68c \ub274\ub9bd\uc2a4(NeurlPS) 2021\uc5d0 \ub450 \ud3b8\uc758 \ub17c\ubb38 \uac8c\uc7ac"},"content":{"rendered":"\n
\"\"<\/figure>\n\n\n\n

\uce74\uce74\uc624\uc5d4\ud130\ud504\ub77c\uc774\uc988\uac00 \uae00\ub85c\ubc8c \uc720\uba85 AI \ud559\ud68c \ub274\ub9bd\uc2a4(NeurIPS) 2021\uc5d0\uc11c \ub450 \ud3b8\uc758 \ub17c\ubb38\uc744 \ub4f1\uc7ac\ud558\ub294 \uc131\uacfc\ub97c \uac70\ub450\uc5c8\uc2b5\ub2c8\ub2e4. \ub274\ub9bd\uc2a4\ub294 \uc778\uacf5\uc9c0\ub2a5, \uae30\uacc4\ud559\uc2b5, \ub1cc\uacfc\ud559 \ubd84\uc57c\uc5d0\uc11c \ucd5c\uace0 \uad8c\uc704\ub97c \uac00\uc9c4 \ud559\ud68c\ub85c, \uc804 \uc138\uacc4 \uc6b0\uc218 \uc5f0\uad6c\uc790\ub4e4\uc758 \ub17c\ubb38 \uc911\uc5d0\uc11c 30% \uc774\ub0b4\uc758 \ub17c\ubb38\ub9cc \uc5c4\uc120\ud574 \uc18c\uac1c\ud558\uace0 \uc788\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

\ud2b9\ud788 \uc62c\ud574 \uce74\uce74\uc624\uc5d4\ud130\ud504\ub77c\uc774\uc988\ub294 \u2018\ucef4\ud4e8\ud130 \ube44\uc804\u2019 \ubd84\uc57c\uc5d0\uc11c \ub450\uac01\uc744 \ub4dc\ub7ec\ub0b4\uba70 \uc6b0\uc218\ud55c \uc5f0\uad6c \uc5ed\ub7c9\uc744 \uc778\uc815 \ubc1b\uc558\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

1) Learning Debiased Representation via Disentangled Feature Augmentation<\/p>\n\n\n\n

\uc774\ubbf8\uc9c0 \ub370\uc774\ud130\uc14b \ud3b8\ud5a5 \ubb38\uc81c\ub97c \ud574\uacb0\ud558\ub294 \ub370\uc774\ud130 \uc99d\uac15 \uae30\ubc95\uc744 \uc0c8\ub86d\uac8c \uc81c\uc548\ud574, \ucd5c\uc0c1\uc704 1%\uc5d0\uac8c\ub9cc \uc8fc\uc5b4\uc9c0\ub294 \uad6c\ub450 \ubc1c\ud45c(oral presentation)\uc758 \uc601\uc608\ub97c \uc548\uc558\uc2b5\ub2c8\ub2e4<\/p>\n\n\n\n

2) SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness<\/p>\n\n\n\n

\uc774\ubbf8\uc9c0 \ub370\uc774\ud130\uc5d0 \uc0c8\ub85c\uc6b4 \uc801\ub300\uc801 \ud6c8\ub828 \ubc29\ubc95\ub860\uc744 \uc801\uc6a9\ud568\uc73c\ub85c\uc368 \ub2e4\uc591\ud55c \uacf5\uaca9\uc744 \ubc29\uc5b4\ud560 \uc218 \uc788\ub294 \uc54c\uace0\ub9ac\uc998\uc744 \uc18c\uac1c\ud574 \ud638\ud3c9\uc744 \ubc1b\uc558\uc2b5\ub2c8\ub2e4.<\/p>\n\n\n\n

\uce74\uce74\uc624\uc5d4\ud130\ud504\ub77c\uc774\uc988\ub294 \uc9c0\uc18d\uc801\uc73c\ub85c \uc88b\uc740 \uae30\uc220 \uc0ac\ub840\ub97c \uacf5\uc720\ud558\uace0 \uc774\ub97c \ub354\uc6b1 \ubc1c\uc804\ub41c \uc11c\ube44\uc2a4\uc758 \ubaa8\uc2b5\uc73c\ub85c \uc120\uc21c\ud658\uc2dc\ud0ac \uc608\uc815\uc785\ub2c8\ub2e4. \ub9ce\uc740 \uad00\uc2ec\uacfc \uc131\uc6d0 \ubd80\ud0c1\ub4dc\ub9bd\ub2c8\ub2e4.<\/p>\n\n\n\n

\uad00\ub828 \uae30\uc0ac \ubcf4\ub7ec\uac00\uae30<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

\uce74\uce74\uc624\uc5d4\ud130\ud504\ub77c\uc774\uc988\uac00 \uae00\ub85c\ubc8c \uc720\uba85 AI \ud559\ud68c \ub274\ub9bd\uc2a4(NeurIPS) 2021\uc5d0\uc11c \ub450 \ud3b8\uc758 \ub17c\ubb38\uc744 \ub4f1\uc7ac\ud558\ub294 \uc131\uacfc\ub97c \uac70\ub450\uc5c8\uc2b5\ub2c8\ub2e4. \ub274\ub9bd\uc2a4\ub294 \uc778\uacf5\uc9c0\ub2a5, \uae30\uacc4\ud559\uc2b5, \ub1cc\uacfc\ud559 \ubd84\uc57c\uc5d0\uc11c \ucd5c\uace0 \uad8c\uc704\ub97c \uac00\uc9c4 \ud559\ud68c\ub85c, \uc804 \uc138\uacc4 \uc6b0\uc218 \uc5f0\uad6c\uc790\ub4e4\uc758 \ub17c\ubb38 \uc911\uc5d0\uc11c 30% \uc774\ub0b4\uc758 \ub17c\ubb38\ub9cc \uc5c4\uc120\ud574 \uc18c\uac1c\ud558\uace0 \uc788\uc2b5\ub2c8\ub2e4. \ud2b9\ud788 \uc62c\ud574 \uce74\uce74\uc624\uc5d4\ud130\ud504\ub77c\uc774\uc988\ub294 \u2018\ucef4\ud4e8\ud130 \ube44\uc804\u2019 \ubd84\uc57c\uc5d0\uc11c \ub450\uac01\uc744 \ub4dc\ub7ec\ub0b4\uba70 \uc6b0\uc218\ud55c \uc5f0\uad6c \uc5ed\ub7c9\uc744 \uc778\uc815 \ubc1b\uc558\uc2b5\ub2c8\ub2e4. 1) Learning Debiased Representation via Disentangled Feature Augmentation […]<\/p>\n","protected":false},"featured_media":2897,"template":"","tags":[85,76,57,56],"acf":[],"_links":{"self":[{"href":"https:\/\/kakaoenterprise.com\/wp-json\/wp\/v2\/about\/1179"}],"collection":[{"href":"https:\/\/kakaoenterprise.com\/wp-json\/wp\/v2\/about"}],"about":[{"href":"https:\/\/kakaoenterprise.com\/wp-json\/wp\/v2\/types\/about"}],"version-history":[{"count":2,"href":"https:\/\/kakaoenterprise.com\/wp-json\/wp\/v2\/about\/1179\/revisions"}],"predecessor-version":[{"id":2617,"href":"https:\/\/kakaoenterprise.com\/wp-json\/wp\/v2\/about\/1179\/revisions\/2617"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/kakaoenterprise.com\/wp-json\/wp\/v2\/media\/2897"}],"wp:attachment":[{"href":"https:\/\/kakaoenterprise.com\/wp-json\/wp\/v2\/media?parent=1179"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kakaoenterprise.com\/wp-json\/wp\/v2\/tags?post=1179"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}