{"id":8102,"date":"2021-03-10T13:13:30","date_gmt":"2021-03-10T18:13:30","guid":{"rendered":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/?p=8102"},"modified":"2026-04-07T12:54:34","modified_gmt":"2026-04-07T16:54:34","slug":"the-weakly-labeled-rand-index","status":"publish","type":"post","link":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/2021\/03\/10\/the-weakly-labeled-rand-index\/","title":{"rendered":"THE WEAKLY-LABELED RAND INDEX"},"content":{"rendered":"<h2>Abstract:<\/h2>\n<p>Synthetic Aperture Sonar (SAS) surveys produce imagery with large regions of transition between seabed types. Due to these regions, it is difficult to label and segment the imagery and, furthermore, challenging to score the image segmentations appropriately. While there are many approaches to quantify performance in standard crisp segmentation schemes, drawing hard boundaries in remote sensing imagery where gradients and regions of uncertainty exist is inappropriate. These cases warrant weak labels and an associated appropriate scoring approach. In this paper, a labeling approach and associated modified version of the Rand index for weakly-labeled data is introduced to address these issues. Results are evaluated with the new index and compared to traditional segmentation evaluation methods. Experimental results on a SAS data set containing must-link and cannot-link labels show that our Weakly-Labeled Rand index scores segmentations appropriately in reference to qualitative performance and is more suitable than traditional quantitative metrics for scoring weakly-labeled data.<\/p>\n<h2>Links:<\/h2>\n<p><a href=\"https:\/\/arxiv.org\/abs\/2103.04872\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-470 size-full\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2016\/09\/arxiv.png\" alt=\"arxiv link of the paper\" width=\"90\" height=\"90\" \/><\/a><a href=\"https:\/\/ieeexplore.ieee.org\/document\/9553182\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone  wp-image-426\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2016\/09\/ieee-300x242.jpg\" alt=\"i triple e link of the paper\" width=\"107\" height=\"86\" srcset=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2016\/09\/ieee-300x242.jpg 300w, https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2016\/09\/ieee.jpg 769w\" sizes=\"auto, (max-width: 107px) 100vw, 107px\" \/><\/a><\/p>\n<h2>Citation:<\/h2>\n<pre><code>D. Stewart, A. Hampton, A. Zare, J. Dale and J. Keller, \"The Weakly-Labeled Rand Index,\" in <em>IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 2313-2316, doi: 10.1109\/IGARSS47720.2021.9553182,<\/em> 2021.\n<\/code><\/pre>\n<pre class=\"verbatim select-on-click\" title=\"click to copy to clipboard\"><code>@Article{Stewart2021WeaklyLabeledRandIndex,\nTitle = {The Weakly-Labeled Rand Index}, \nAuthor = {Dylan Stewart and Anna Hampton and Alina Zare and Jeff Dale and James Keller},  \nJournal = {IEEE International Geoscience and Remote Sensing Symposium (IGARSS)}, \nVolume = {},  \npages={2313-2316},\ndoi={10.1109\/IGARSS47720.2021.9553182},\nYear = {2021}  \n}<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>Abstract: Synthetic Aperture Sonar (SAS) surveys produce imagery with large regions of transition between seabed types. Due to these regions, it is difficult to label and segment the imagery and, furthermore, challenging to score the image segmentations appropriately. While there are many approaches to quantify performance in standard crisp segmentation schemes, drawing hard boundaries in [&hellip;]<\/p>\n","protected":false},"author":28,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"single-templates\/single-sidebar-none.php","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"featured_post":"off","footnotes":"","_links_to":"","_links_to_target":""},"categories":[17,9,13],"tags":[53,285,411,621,655,659,713,717,729,793],"class_list":["post-8102","post","type-post","status-publish","format-standard","hentry","category-conference_paper","category-news","category-publication","tag-uncertain-imprecise-labels","tag-evaluation","tag-label-uncertainty","tag-remote-sensing","tag-scoring","tag-segmentation","tag-super-pixels","tag-superpixel","tag-synthetic-aperture-sonar","tag-weakly-labeled"],"acf":[],"_links":{"self":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/8102","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/users\/28"}],"replies":[{"embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/comments?post=8102"}],"version-history":[{"count":2,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/8102\/revisions"}],"predecessor-version":[{"id":16449,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/8102\/revisions\/16449"}],"wp:attachment":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/media?parent=8102"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/categories?post=8102"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/tags?post=8102"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}