{"id":5974,"date":"2021-05-11T11:40:43","date_gmt":"2021-05-11T03:40:43","guid":{"rendered":"https:\/\/pairlabs.ai\/?p=5974"},"modified":"2021-05-17T11:52:07","modified_gmt":"2021-05-17T03:52:07","slug":"icmr2021-grand-challenge-the-pair-competition-ended-successfully","status":"publish","type":"post","link":"https:\/\/pairlabs.ai\/en\/icmr2021-grand-challenge-the-pair-competition-ended-successfully\/","title":{"rendered":"ICMR2021 Grand Challenge: The PAIR competition ended successfully"},"content":{"rendered":"<p>The \u201cICMR2021 Grand Challenge \u2013 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries\u201d co-sponsored by MediaTek Inc., PAIR Labs and\u00a0<a href=\"http:\/\/ivs.ee.nctu.edu.tw\/ivs\/index.php\/advisor\">iVS Lab (Directed by Prof. Jiun-In Guo)<\/a>\u00a0has successfully concluded. This competition is mainly aimed at the unique transportation and road conditions in Asia. After two months of qualification competition and four weeks of final competition, the winners and special awards were finally released.<\/p>\n<p>&nbsp;<\/p>\n<h3>Award Winners<\/h3>\n<ul>\n<li>Champion: as798792 (\u570b\u7acb\u53f0\u5357\u5927\u5b78)<\/li>\n<li>First Runner-up: Deep Learner (\u5317\u4eac\u4ea4\u901a\u5927\u5b78)<\/li>\n<li>Second Runner-up:\u00a0UCBH (\u570b\u7acb\u6210\u529f\u5927\u5b78\u96fb\u901a\u6240)<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3>Special Awards<\/h3>\n<ul>\n<li>Best accuracy award: as798792 (\u570b\u7acb\u53f0\u5357\u5927\u5b78)<\/li>\n<li>Best bicycle detection award:\u00a0as798792 (\u570b\u7acb\u53f0\u5357\u5927\u5b78)<\/li>\n<li>Best scooter detection award:\u00a0abcda (\u570b\u7acb\u81fa\u7063\u5e2b\u7bc4\u5927\u5b78\u8cc7\u5de5\u7cfb)<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3>Final Evaluation Result<\/h3>\n<table>\n<tbody>\n<tr>\n<td rowspan=\"2\" width=\"66\"><strong>Team<\/strong><\/td>\n<td colspan=\"3\" width=\"105\"><strong>Accuracy (%)<\/strong><\/td>\n<td rowspan=\"2\" width=\"47\"><strong>Model Size (MByte)<\/strong><\/td>\n<td rowspan=\"2\" width=\"55\"><strong>Complexity<\/strong><\/p>\n<p><strong>(FLOPs)<\/strong><\/td>\n<td rowspan=\"2\" width=\"51\"><strong>Speed<\/strong><\/p>\n<p><strong>(s\/image)<\/strong><\/td>\n<\/tr>\n<tr>\n<td width=\"28\"><strong>mAP<\/strong><\/td>\n<td width=\"38\"><strong>scooter<\/strong><\/td>\n<td width=\"38\"><strong>bicycle<\/strong><\/td>\n<\/tr>\n<tr>\n<td width=\"66\">as798792<\/td>\n<td width=\"28\">59<\/td>\n<td width=\"38\">53.5<\/td>\n<td width=\"38\">53.5<\/td>\n<td width=\"47\">12<\/td>\n<td width=\"55\">5.04G<\/td>\n<td width=\"51\">24.57<\/td>\n<\/tr>\n<tr>\n<td width=\"66\">Deep Learner<\/td>\n<td width=\"28\">53.2<\/td>\n<td width=\"38\">51.2<\/td>\n<td width=\"38\">31.5.<\/td>\n<td width=\"47\">28.53<\/td>\n<td width=\"55\">2.46G<\/td>\n<td width=\"51\">18.82<\/td>\n<\/tr>\n<tr>\n<td width=\"66\">UCBH<\/td>\n<td width=\"28\">53.7<\/td>\n<td width=\"38\">62<\/td>\n<td width=\"38\">7.1<\/td>\n<td width=\"47\">28.62<\/td>\n<td width=\"55\">23.63G<\/td>\n<td width=\"51\">105.83<\/td>\n<\/tr>\n<tr>\n<td width=\"66\">yifu<\/td>\n<td width=\"28\">42.5<\/td>\n<td width=\"38\">54.2<\/td>\n<td width=\"38\">8.7<\/td>\n<td width=\"47\">24.59<\/td>\n<td width=\"55\">12.16G<\/td>\n<td width=\"51\">54.95<\/td>\n<\/tr>\n<tr>\n<td width=\"66\">pui pui<\/td>\n<td width=\"28\">52.4<\/td>\n<td width=\"38\">63.1<\/td>\n<td width=\"38\">0.3<\/td>\n<td width=\"47\">84.72<\/td>\n<td width=\"55\">64.32G<\/td>\n<td width=\"51\">60.18<\/td>\n<\/tr>\n<tr>\n<td width=\"66\">abcda<\/td>\n<td width=\"28\">56.8<\/td>\n<td width=\"38\">63.3<\/td>\n<td width=\"38\">14.6<\/td>\n<td width=\"47\">192.36<\/td>\n<td width=\"55\">390.83G<\/td>\n<td width=\"51\">&#8211;<\/td>\n<\/tr>\n<tr>\n<td width=\"66\">IRIS<\/td>\n<td width=\"28\">49.9<\/td>\n<td width=\"38\">60.1<\/td>\n<td width=\"38\">4.4<\/td>\n<td width=\"47\">76.06<\/td>\n<td width=\"55\">&#8211;<\/td>\n<td width=\"51\">418.47<\/td>\n<\/tr>\n<tr>\n<td width=\"66\">lsm98<\/td>\n<td width=\"28\">37.6<\/td>\n<td width=\"38\">45.5<\/td>\n<td width=\"38\">&#8211;<\/td>\n<td width=\"47\">155<\/td>\n<td width=\"55\">&#8211;<\/td>\n<td width=\"51\">2497.1<\/td>\n<\/tr>\n<tr>\n<td width=\"66\">johnson0213<\/td>\n<td width=\"28\">&#8211;<\/td>\n<td width=\"38\">&#8211;<\/td>\n<td width=\"38\">&#8211;<\/td>\n<td width=\"47\">121<\/td>\n<td width=\"55\">116.12G<\/td>\n<td width=\"51\">&#8211;<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>&nbsp;<\/p>\n<h3>Final Score<\/h3>\n<table>\n<tbody>\n<tr>\n<td rowspan=\"2\" width=\"94\"><strong>Team<\/strong><\/td>\n<td colspan=\"4\" width=\"186\"><strong>Partial Score<\/strong><\/td>\n<td rowspan=\"2\" width=\"44\"><strong>Final Score<\/strong><\/td>\n<\/tr>\n<tr>\n<td width=\"38\"><strong>mAP<\/strong><\/td>\n<td width=\"38\"><strong>Size<\/strong><\/td>\n<td width=\"65\"><strong>Complexity<\/strong><\/td>\n<td width=\"46\"><strong>Speed<\/strong><\/td>\n<\/tr>\n<tr>\n<td width=\"94\">as798792<\/td>\n<td width=\"38\">40<\/td>\n<td width=\"38\">15<\/td>\n<td width=\"65\">13<\/td>\n<td width=\"46\">27<\/td>\n<td width=\"44\">95<\/td>\n<\/tr>\n<tr>\n<td width=\"94\">Deep Learner<\/td>\n<td width=\"38\">25<\/td>\n<td width=\"38\">11<\/td>\n<td width=\"65\">15<\/td>\n<td width=\"46\">30<\/td>\n<td width=\"44\">81<\/td>\n<\/tr>\n<tr>\n<td width=\"94\">UCBH<\/td>\n<td width=\"38\">30<\/td>\n<td width=\"38\">9<\/td>\n<td width=\"65\">9<\/td>\n<td width=\"46\">13<\/td>\n<td width=\"44\">61<\/td>\n<\/tr>\n<tr>\n<td width=\"94\">yifu<\/td>\n<td width=\"38\">10<\/td>\n<td width=\"38\">13<\/td>\n<td width=\"65\">11<\/td>\n<td width=\"46\">22<\/td>\n<td width=\"44\">56<\/td>\n<\/tr>\n<tr>\n<td width=\"94\">pui pui<\/td>\n<td width=\"38\">20<\/td>\n<td width=\"38\">6<\/td>\n<td width=\"65\">6<\/td>\n<td width=\"46\">18<\/td>\n<td width=\"44\">50<\/td>\n<\/tr>\n<tr>\n<td width=\"94\">abcda<\/td>\n<td width=\"38\">35<\/td>\n<td width=\"38\">0<\/td>\n<td width=\"65\">2<\/td>\n<td width=\"46\">0<\/td>\n<td width=\"44\">37<\/td>\n<\/tr>\n<tr>\n<td width=\"94\">IRIS<\/td>\n<td width=\"38\">15<\/td>\n<td width=\"38\">8<\/td>\n<td width=\"65\">0<\/td>\n<td width=\"46\">9<\/td>\n<td width=\"44\">32<\/td>\n<\/tr>\n<tr>\n<td width=\"94\">lsm98<\/td>\n<td width=\"38\">5<\/td>\n<td width=\"38\">2<\/td>\n<td width=\"65\">0<\/td>\n<td width=\"46\">4<\/td>\n<td width=\"44\">11<\/td>\n<\/tr>\n<tr>\n<td width=\"94\">johnson0213<\/td>\n<td width=\"38\">0<\/td>\n<td width=\"38\">4<\/td>\n<td width=\"65\">4<\/td>\n<td width=\"46\">0<\/td>\n<td width=\"44\">8<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n","protected":false},"excerpt":{"rendered":"<p>The \u201cICMR2021 Grand Challenge \u2013 Embedded Deep Learning Object Detection Model Compression Competition for Traffic in Asian Countries\u201d co-sponsored by MediaTek Inc., PAIR Labs and\u00a0iVS Lab (Directed by Prof. Jiun-In Guo)\u00a0has successfully concluded. This competition is mainly aimed at the unique transportation and road conditions in Asia. After two months of qualification competition and four [&hellip;]<\/p>\n","protected":false},"author":16,"featured_media":5816,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[126],"tags":[],"class_list":["post-5974","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category--en"],"_links":{"self":[{"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/posts\/5974","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/comments?post=5974"}],"version-history":[{"count":4,"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/posts\/5974\/revisions"}],"predecessor-version":[{"id":5990,"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/posts\/5974\/revisions\/5990"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/media\/5816"}],"wp:attachment":[{"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/media?parent=5974"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/categories?post=5974"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/pairlabs.ai\/en\/wp-json\/wp\/v2\/tags?post=5974"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}