{"id":1336,"date":"2016-09-11T17:51:28","date_gmt":"2016-09-11T22:51:28","guid":{"rendered":"https:\/\/faculty.eng.ufl.edu\/alina-zare\/?p=1336"},"modified":"2026-02-18T11:29:08","modified_gmt":"2026-02-18T16:29:08","slug":"zare2016miace","status":"publish","type":"post","link":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/2016\/09\/11\/zare2016miace\/","title":{"rendered":"Discriminative Multiple Instance Hyperspectral Target Characterization"},"content":{"rendered":"<h2>Abstract:<\/h2>\n<p>In this paper, two methods for multiple instance target characterization, MI-SMF and MI-ACE, are presented. MI-SMF and MI-ACE estimate a discriminative target signature from imprecisely-labeled and mixed training data. In many applications, such as sub-pixel target detection in remotely-sensed hyperspectral imagery, accurate pixel-level labels on training data is often unavailable and infeasible to obtain. Furthermore, since sub-pixel targets are smaller in size than the resolution of a single pixel, training data is comprised only of mixed data points (in which target training points are mixtures of responses from both target and non-target classes). Results show improved, consistent performance over existing multiple instance concept learning methods on several hyperspectral sub-pixel target detection problems.<\/p>\n<h2>Links:<\/h2>\n<p><a href=\"http:\/\/ieeexplore.ieee.org\/document\/8051065\/authors?ctx=authors\"><img decoding=\"async\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2016\/09\/ieee.jpg\" alt=\"\u201cIeee\" height=\"50\" border=\"2\" \/><\/a> <a href=\"http:\/\/arxiv.org\/abs\/1606.06354\"><img decoding=\"async\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2016\/09\/arxiv.png\" alt=\"\u201cArXiv\" height=\"50\" border=\"2\" \/><\/a> <a href=\"https:\/\/github.com\/GatorSense\/MIACE\"><img decoding=\"async\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2016\/09\/GitHub-Mark-e1482256611783.png\" alt=\"\u201cCode\u201d\" height=\"50\" border=\"2\" \/><\/a> <a href=\"https:\/\/codeocean.com\/2017\/09\/26\/multiple-instance-discriminative-target-characterization\/metadata\"><img decoding=\"async\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2017\/09\/CodeOcean.png\" alt=\"\u201cCodeOcean\" height=\"50\" border=\"2\" \/><\/a><\/p>\n<h2>Citation:<\/h2>\n<pre><code>A. Zare, C. Jiao, and T. Glenn, \u201cDiscriminative Multiple Instance Hyperspectral Target Characterization,\u201d <em>IEEE Trans. Pattern Anal Mach. Inteli.<\/em>, vol. 40, iss. 10, pp. 2342-2354, 2018. <\/code><\/pre>\n<pre><code>@Article{zare2016miace,\nAuthor = {Zare, Alina and Jiao, Changzhe and Glenn, Taylor},\nTitle = {Discriminative Multiple Instance Hyperspectral Target Characterization},\nJournal = {<em>IEEE Trans. Pattern Anal. Mach. Inteli.<\/em>},\nYear = {2018},\nvolume = {40},\nnumber = {10},\npages = {2342-2354},\nmonth = {Oct.},\ndoi = {10.1109\/TPAMI.2017.2756632},\n}\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>Abstract: In this paper, two methods for multiple instance target characterization, MI-SMF and MI-ACE, are presented. MI-SMF and MI-ACE estimate a discriminative target signature from imprecisely-labeled and mixed training data. In many applications, such as sub-pixel target detection in remotely-sensed hyperspectral imagery, accurate pixel-level labels on training data is often unavailable and infeasible to obtain. [&hellip;]<\/p>\n","protected":false},"author":28,"featured_media":2968,"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":"","footnotes":"","_links_to":"","_links_to_target":""},"categories":[5,19],"tags":[53,365,487,733],"class_list":["post-1336","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-featured","category-journal_paper","tag-uncertain-imprecise-labels","tag-hyperspectral","tag-multiple-instance","tag-target-detection"],"acf":[],"_links":{"self":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/1336","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=1336"}],"version-history":[{"count":1,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/1336\/revisions"}],"predecessor-version":[{"id":15019,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/1336\/revisions\/15019"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/media\/2968"}],"wp:attachment":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/media?parent=1336"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/categories?post=1336"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/tags?post=1336"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}