{"id":223,"date":"2018-10-29T12:37:11","date_gmt":"2018-10-29T11:37:11","guid":{"rendered":"https:\/\/project.inria.fr\/epitome\/?page_id=223"},"modified":"2018-10-31T15:28:01","modified_gmt":"2018-10-31T14:28:01","slug":"inc_learn","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/epitome\/inc_learn\/","title":{"rendered":"Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data"},"content":{"rendered":"<p><\/p>\n<h1>Paper<\/h1>\n<p>The paper can be found <a href=\"https:\/\/arxiv.org\/abs\/1810.12448\">here<\/a>.<\/p>\n<hr \/>\n<h1>Additional Results<\/h1>\n<p>For the sake of more compact visualization in visual results of the paper, instead of multiple binary predicted maps, multi-class predictions are provided by assigning each pixel to the class, for which the highest probability is produced (see Fig. 9).<\/p>\n<p>The original binary maps by only our approach for the close-ups from the Luxcarta dataset are illustrated in the figure below:<\/p>\n<table style=\"width: 100%;\">\n<tbody>\n<tr>\n<td><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/project.inria.fr\/epitome\/files\/2018\/10\/inc_learn_results.png\" alt=\"\" width=\"998\" height=\"2153\" \/><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<hr \/>\n<h1>Source Code<\/h1>\n<p>If you are interested in the code, please fill in the form below:<\/p>\n<p>\n<div class=\"wpcf7 no-js\" id=\"wpcf7-f215-o1\" lang=\"en-US\" dir=\"ltr\" data-wpcf7-id=\"215\"><form action=\"\/epitome\/wp-json\/wp\/v2\/pages\/223#wpcf7-f215-o1\" method=\"post\" class=\"wpcf7-form init\" novalidate=\"novalidate\" data-status=\"init\">\n<div style=\"display: none;\">\n<input type=\"hidden\" name=\"_wpcf7\" value=\"215\" \/>\n<input type=\"hidden\" name=\"_wpcf7_version\" value=\"6.0.6\" \/>\n<input type=\"hidden\" name=\"_wpcf7_locale\" value=\"en_US\" \/>\n<input type=\"hidden\" name=\"_wpcf7_unit_tag\" value=\"wpcf7-f215-o1\" \/>\n<input type=\"hidden\" name=\"_wpcf7_container_post\" value=\"0\" \/>\n<input type=\"hidden\" name=\"_wpcf7_posted_data_hash\" value=\"\" \/>\n<\/div>\n<p><label> Name (required)<br \/>\n<span class=\"wpcf7-form-control-wrap\" data-name=\"your-name\"><input class=\"wpcf7-form-control wpcf7-text wpcf7-validates-as-required\" aria-required=\"true\" aria-invalid=\"false\" value=\"\" type=\"text\" name=\"your-name\" \/><\/span> <\/label>\n<\/p>\n<p><label> Email (required)<br \/>\n<span class=\"wpcf7-form-control-wrap\" data-name=\"your-email\"><input class=\"wpcf7-form-control wpcf7-email wpcf7-validates-as-required wpcf7-text wpcf7-validates-as-email\" aria-required=\"true\" aria-invalid=\"false\" value=\"\" type=\"email\" name=\"your-email\" \/><\/span> <\/label>\n<\/p>\n<p><label> Institution (required)<br \/>\n<span class=\"wpcf7-form-control-wrap\" data-name=\"your-institution\"><input class=\"wpcf7-form-control wpcf7-text wpcf7-validates-as-required\" aria-required=\"true\" aria-invalid=\"false\" value=\"\" type=\"text\" name=\"your-institution\" \/><\/span> <\/label>\n<\/p>\n<p><input class=\"wpcf7-form-control wpcf7-submit has-spinner\" type=\"submit\" value=\"Submit Request\" \/>\n<\/p><div class=\"wpcf7-response-output\" tabindex=\"-1\"><\/div>\n<\/form>\n<\/div>\n<\/p>","protected":false},"excerpt":{"rendered":"<p>Paper The paper can be found here. Additional Results For the sake of more compact visualization in visual results of the paper, instead of multiple binary predicted maps, multi-class predictions are provided by assigning each pixel to the class, for which the highest probability is produced (see Fig. 9). The\u2026<\/p>\n<p> <a class=\"continue-reading-link\" href=\"https:\/\/project.inria.fr\/epitome\/inc_learn\/\"><span>Continue reading<\/span><i class=\"crycon-right-dir\"><\/i><\/a> <\/p>\n","protected":false},"author":1323,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-223","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/project.inria.fr\/epitome\/wp-json\/wp\/v2\/pages\/223","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/project.inria.fr\/epitome\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/project.inria.fr\/epitome\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/epitome\/wp-json\/wp\/v2\/users\/1323"}],"replies":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/epitome\/wp-json\/wp\/v2\/comments?post=223"}],"version-history":[{"count":6,"href":"https:\/\/project.inria.fr\/epitome\/wp-json\/wp\/v2\/pages\/223\/revisions"}],"predecessor-version":[{"id":235,"href":"https:\/\/project.inria.fr\/epitome\/wp-json\/wp\/v2\/pages\/223\/revisions\/235"}],"wp:attachment":[{"href":"https:\/\/project.inria.fr\/epitome\/wp-json\/wp\/v2\/media?parent=223"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}