{"id":1099,"date":"2021-11-24T06:00:00","date_gmt":"2021-11-23T21:00:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=1099"},"modified":"2021-11-24T06:00:00","modified_gmt":"2021-11-23T21:00:00","slug":"florence-computer-vision%e3%81%ae%e5%9f%ba%e7%a4%8e%e3%83%a2%e3%83%87%e3%83%ab","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=1099","title":{"rendered":"Florence: Computer Vision\u306e\u57fa\u790e\u30e2\u30c7\u30eb"},"content":{"rendered":"\n<ul class=\"wp-block-list\"><li><strong>Florence: A New Foundation Model for Computer Vision\u00a0<\/strong>[97.3]<br>\u591a\u69d8\u306a\u5927\u898f\u6a21\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3055\u308c\u3001\u5e45\u5e83\u3044\u4e0b\u6d41\u30bf\u30b9\u30af\u306b\u9069\u5fdc\u3067\u304d\u308b\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30d3\u30b8\u30e7\u30f3\u57fa\u76e4\u30e2\u30c7\u30eb\u3067\u3042\u308bFlorence\u3092\u5c0e\u5165\u3059\u308b\u3002 Web\u30b9\u30b1\u30fc\u30eb\u306e\u753b\u50cf\u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u304b\u3089\u666e\u904d\u7684\u306a\u8996\u899a\u8a00\u8a9e\u8868\u73fe\u3092\u7d44\u307f\u8fbc\u3080\u3053\u3068\u3067\u3001\u30d5\u30a3\u30ec\u30f3\u30c4\u30a7\u30e2\u30c7\u30eb\u306f\u69d8\u3005\u306a\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30d3\u30b8\u30e7\u30f3\u30bf\u30b9\u30af\u306b\u5bb9\u6613\u306b\u9069\u5fdc\u3067\u304d\u308b\u3002 Florence\u306f44\u306e\u4ee3\u8868\u7684\u306a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306e\u904e\u534a\u6570\u306b\u304a\u3044\u3066\u3001\u6700\u5148\u7aef\u306e\u65b0\u305f\u306a\u7d50\u679c\u3092\u9054\u6210\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2111.11432v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2111.11432v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 22 Nov 2021 18:59:55 GMT)<ul><li>\u753b\u50cf\u5206\u91ce\u306b\u304a\u3051\u308b\u57fa\u790e\u30e2\u30c7\u30eb\u3068\u3057\u3066Space-Time-Modality\u65b9\u5411\u306b\u304a\u3044\u3066\u6709\u52b9\u3067\u3042\u308a\u3001zero\/few-shot\/fine-tuning\u306e\u4f55\u308c\u3082\u52d5\u4f5c\u3059\u308b\u3082\u306e\u3092\u69cb\u7bc9\u3002\u591a\u304f\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067SoTA\u3092\u9054\u6210\u3002VQA v2\u306780\u3092\u8d85\u3048\u305f\u306e\u306f\u521d\u3081\u3066\u3067\u306f\uff1f\u3068\u601d\u3046\u3002<ul><li>Space:  \u30b7\u30fc\u30f3\u8a8d\u8b58 \u2192 \u7d30\u304b\u3044\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u306e\u8a8d\u8b58\u3084\u30bb\u30b0\u30e1\u30f3\u30c6\u30fc\u30b7\u30e7\u30f3\u306a\u3069<\/li><li>Time: \u9759\u7684\u306a\u753b\u50cf \u2192 \u30c0\u30a4\u30ca\u30df\u30c3\u30af\u306a\u52d5\u4f5c\u306e\u8a8d\u8b58\u3084\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u30c8\u30e9\u30c3\u30ad\u30f3\u30b0\u306a\u3069<\/li><li>Modality: RGB only \u2192 \u6df1\u5ea6\u306e\u5229\u7528\u3084\u30ad\u30e3\u30d7\u30b7\u30e7\u30cb\u30f3\u30b0\u306a\u3069\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u306a\u65b9\u5411<\/li><\/ul><\/li><li>FLD-900M(FLorenceDataset-900M)\u3068\u3044\u30469\u5104\u306e\u753b\u50cf-\u30c6\u30ad\u30b9\u30c8\u30da\u30a2\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3001FLOD-9M (FLorence Object detection Dataset-9M)\u3068\u3044\u30469M\u30a4\u30e1\u30fc\u30b8\u300125K\u30ab\u30c6\u30b4\u30ea\u300133M BBOX\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306a\u3069\u5229\u7528\u3057\u3066\u3044\u308b\u30c7\u30fc\u30bf\u3082\u5927\u898f\u6a21\u3002<\/li><li><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/a-holistic-representation-toward-integrative-ai\/\">A holistic representation toward integrative AI &#8211; Microsoft Research<\/a>\u306b\u5411\u3051\u305f\u7b2c\u4e00\u6b69\u3068\u306e\u3053\u3068\u3067\u4eca\u5f8c\u3082\u671f\u5f85\u5927\u3002<\/li><\/ul><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Florence: A New Foundation Model for Computer Vision\u00a0[97.3]\u591a\u69d8\u306a\u5927\u898f\u6a21\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3055\u308c\u3001\u5e45\u5e83\u3044\u4e0b\u6d41\u30bf\u30b9\u30af\u306b\u9069\u5fdc\u3067\u304d\u308b\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30d3\u30b8\u30e7\u30f3\u57fa\u76e4\u30e2\u30c7\u30eb &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=1099\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;Florence: Computer Vision\u306e\u57fa\u790e\u30e2\u30c7\u30eb&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[524,567],"class_list":["post-1099","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-524","tag-567"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1099","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1099"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1099\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1099"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1099"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1099"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}