{"id":1598,"date":"2022-03-09T05:00:00","date_gmt":"2022-03-08T20:00:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=1598"},"modified":"2022-03-09T05:00:00","modified_gmt":"2022-03-08T20:00:00","slug":"ditdocument-image-transformer-%e6%96%87%e6%9b%b8%e6%a7%8b%e9%80%a0%e8%aa%8d%e8%ad%98","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=1598","title":{"rendered":"DiT(Document Image Transformer): Transformer + MIM\u306a\u4e8b\u524d\u5b66\u7fd2\u306b\u3088\u308b\u6587\u66f8\u69cb\u9020\u8a8d\u8b58"},"content":{"rendered":"\n<ul class=\"wp-block-list\"><li><strong>DiT: Self-supervised Pre-training for Document Image Transformer&nbsp;<\/strong>[85.8]<br>\u81ea\u5df1\u6559\u5e2b\u4ed8\u304d\u6587\u66f8\u753b\u50cf\u5909\u63db\u30e2\u30c7\u30eb\u3067\u3042\u308bDiT\u3092\u63d0\u6848\u3059\u308b\u3002 \u3055\u307e\u3056\u307e\u306a\u30d3\u30b8\u30e7\u30f3\u30d9\u30fc\u30b9\u306eDocument AI\u30bf\u30b9\u30af\u3067\u306f,\u30d0\u30c3\u30af\u30dc\u30fc\u30f3\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3068\u3057\u3066DiT\u3092\u6d3b\u7528\u3057\u3066\u3044\u307e\u3059\u3002 \u5b9f\u9a13\u7d50\u679c\u304b\u3089, \u81ea\u5df1\u6559\u5e2b\u4ed8\u304d\u4e8b\u524d\u8a13\u7df4\u578bDiT\u30e2\u30c7\u30eb\u306b\u3088\u308a, \u65b0\u305f\u306a\u6700\u5148\u7aef\u7d50\u679c\u304c\u5f97\u3089\u308c\u308b\u3053\u3068\u304c\u793a\u3055\u308c\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2203.02378v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2203.02378v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Fri, 4 Mar 2022 15:34:46 GMT)<ul><li>Masked Image Modeling\u306a\u5927\u898f\u6a21\u4e8b\u524d\u5b66\u7fd2\u3092\u884c\u3044Document Image Transformer\u3092\u69cb\u7bc9\u3001document image classi\ufb01cation\u3001document layout analysis\u3001 table detection\u3067SoTA\u3068\u306e\u3053\u3068\u3002OCR\u306e\u524d\u51e6\u7406\u306a\u3069\u306b\u91cd\u8981\u3067\u3042\u308a\u3001\u30e2\u30c7\u30eb\u304c\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u306e\u304c\u3042\u308a\u304c\u305f\u3044\u3002<\/li><\/ul><ul><li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/microsoft\/unilm\/tree\/master\/dit\">unilm\/dit at master \u00b7 microsoft\/unilm \u00b7 GitHub<\/a><\/li><\/ul><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>DiT: Self-supervised Pre-training for Document Image Transformer&nbsp;[85.8]\u81ea\u5df1\u6559\u5e2b\u4ed8\u304d\u6587\u66f8\u753b\u50cf\u5909\u63db\u30e2\u30c7\u30eb\u3067\u3042\u308bDiT\u3092\u63d0\u6848\u3059\u308b\u3002 \u3055\u307e\u3056\u307e\u306a\u30d3 &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=1598\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;DiT(Document Image Transformer): Transformer + MIM\u306a\u4e8b\u524d\u5b66\u7fd2\u306b\u3088\u308b\u6587\u66f8\u69cb\u9020\u8a8d\u8b58&#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":[117,415],"class_list":["post-1598","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-document-understanding","tag-transformer"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1598","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=1598"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1598\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1598"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1598"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1598"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}