{"id":884,"date":"2022-10-18T18:24:00","date_gmt":"2022-10-18T16:24:00","guid":{"rendered":"http:\/\/matlas.astro.unistra.fr\/WP\/?p=884"},"modified":"2022-10-19T15:13:40","modified_gmt":"2022-10-19T13:13:40","slug":"multi-scale-gridded-gabor-attention-for-cirrus-segmentation","status":"publish","type":"post","link":"https:\/\/matlas.astro.unistra.fr\/WP\/?p=884","title":{"rendered":"Multi-scale gridded Gabor attention for cirrus segmentation"},"content":{"rendered":"\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"344\" height=\"256\" src=\"http:\/\/matlas.astro.unistra.fr\/WP\/wp-content\/uploads\/2022\/02\/Capture-de\u0301cran-2022-02-28-a\u0300-12.18.08.png\" alt=\"\" class=\"wp-image-885\" srcset=\"https:\/\/matlas.astro.unistra.fr\/WP\/wp-content\/uploads\/2022\/02\/Capture-de\u0301cran-2022-02-28-a\u0300-12.18.08.png 344w, https:\/\/matlas.astro.unistra.fr\/WP\/wp-content\/uploads\/2022\/02\/Capture-de\u0301cran-2022-02-28-a\u0300-12.18.08-300x223.png 300w\" sizes=\"auto, (max-width: 344px) 100vw, 344px\" \/><figcaption>Richards et al. 2022<\/figcaption><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">In this paper, we address the challenge of segmenting global contaminants in large images. The precise delineation of such structures requires ample global context alongside un- derstanding of textural patterns. CNNs specialise in the latter, though their ability to generate global features is limited. At- tention has been used to measure long range dependencies in images, capturing global context, however this incurs a large computational cost. <\/p>\n\n\n\n<!--more-->\n\n\n\n<p class=\"wp-block-paragraph\">We propose a gridded attention mecha- nism to address this limitation, greatly increasing efficiency by processing multi-scale features into tiles with smaller resolution. We also enhance the attention mechanism for increased sensitivity to texture orientation, by measuring cor- relations across features dependent on different orientations, in addition to channel and positional attention. We present results on a new dataset of astronomical images, where the task is segmenting large contaminating dust clouds.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Richards et al., 2022 <a href=\"https:\/\/seafile.unistra.fr\/f\/fc28a2e461664f4dbea1\/\" data-type=\"URL\" data-id=\"https:\/\/seafile.unistra.fr\/f\/fc28a2e461664f4dbea1\/\">presented <\/a> at <a href=\"https:\/\/2022.ieeeicip.org\/\">ICIP 2022 <\/a>          (<a href=\"https:\/\/seafile.unistra.fr\/f\/37e0a30e4fd14f93a813\/\">Poster<\/a>)<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In this paper, we address the challenge of segmenting global contaminants in large images. The precise delineation of such structures requires ample global context alongside un- derstanding of textural patterns. CNNs specialise in the latter, though their ability to generate global features is limited. At- tention has been used to measure long range dependencies in &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/matlas.astro.unistra.fr\/WP\/?p=884\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Multi-scale gridded Gabor attention for cirrus segmentation&#8221;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-884","post","type-post","status-publish","format-standard","hentry","category-publications"],"_links":{"self":[{"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=\/wp\/v2\/posts\/884","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=884"}],"version-history":[{"count":3,"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=\/wp\/v2\/posts\/884\/revisions"}],"predecessor-version":[{"id":912,"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=\/wp\/v2\/posts\/884\/revisions\/912"}],"wp:attachment":[{"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=884"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=884"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/matlas.astro.unistra.fr\/WP\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=884"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}