{"id":6581,"date":"2025-04-15T04:03:00","date_gmt":"2025-04-14T19:03:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6581"},"modified":"2025-04-15T04:03:00","modified_gmt":"2025-04-14T19:03:00","slug":"docsam-unified-document-image-segmentation-via-query-decomposition-and-heterogeneous-mixed-learning","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6581","title":{"rendered":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning\u00a0<\/strong>[39.1]<br>\u6587\u66f8\u753b\u50cf\u306e\u30bb\u30b0\u30e1\u30f3\u30c6\u30fc\u30b7\u30e7\u30f3\u306f\u3001\u6587\u66f8\u89e3\u6790\u3068\u8a8d\u8b58\u306b\u4e0d\u53ef\u6b20\u3067\u3042\u308b\u3002 \u65e2\u5b58\u306e\u30e1\u30bd\u30c3\u30c9\u306f\u3053\u308c\u3089\u306e\u30bf\u30b9\u30af\u3092\u5225\u3005\u306b\u51e6\u7406\u3057\u3001\u305d\u306e\u7d50\u679c\u3001\u4e00\u822c\u5316\u3068\u30ea\u30bd\u30fc\u30b9\u306e\u6d6a\u8cbb\u304c\u5236\u9650\u3055\u308c\u308b\u3002 \u672c\u7a3f\u3067\u306f,\u69d8\u3005\u306a\u6587\u66f8\u753b\u50cf\u30bb\u30b0\u30e1\u30f3\u30c6\u30fc\u30b7\u30e7\u30f3\u30bf\u30b9\u30af\u7528\u306b\u8a2d\u8a08\u3055\u308c\u305f\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u30d9\u30fc\u30b9\u306e\u7d71\u5408\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308bDocSAM\u3092\u7d39\u4ecb\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2504.04085v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2504.04085v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sat, 05 Apr 2025 07:14:53 GMT)<\/li>\n\n\n\n<li>MLLM\u5168\u76db\u306e\u73fe\u72b6\u3067\u3082\u91cd\u8981\u306aDocument image segmentation\u306b\u3064\u3044\u3066\u300cDocSAM integrates layout analysis, multi-grained text segmentation, and table structure decomposition into a single model, reducing the need for specialized models and enhancing efficiency.\u300d\u3068\u3044\u3046\u624b\u6cd5\u306e\u63d0\u6848\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/xhli-git\/DocSAM\">GitHub &#8211; xhli-git\/DocSAM<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[117],"class_list":["post-6581","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-document-understanding"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6581","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=6581"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6581\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6581"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6581"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6581"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}