{"id":13809,"date":"2025-04-04T12:54:38","date_gmt":"2025-04-04T17:54:38","guid":{"rendered":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/?p=13809"},"modified":"2026-04-15T01:27:49","modified_gmt":"2026-04-15T05:27:49","slug":"congratulations-to-dr-aditya-dutt-for-a-successful-dissertation-defense","status":"publish","type":"post","link":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/2025\/04\/04\/congratulations-to-dr-aditya-dutt-for-a-successful-dissertation-defense\/","title":{"rendered":"Congratulations to Dr. Aditya Dutt for a Successful Dissertation Defense!"},"content":{"rendered":"<p>Congratulations to <strong>Dr. Aditya Dutt<\/strong> for successfully passing his PhD dissertation exam!<\/p>\n<p><img decoding=\"async\" class=\"alignnone wp-image-1948 size-medium\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2025\/04\/adityadefense3-e1743789374434.png\" alt=\"\" width=\"700\" \/><\/p>\n<p>Dr. Dutt\u2019s research introduced the Contrastive MultiModal Alignment Network (COMMANet), a novel approach to shared manifold-based domain translation and fusion.<\/p>\n<p><img decoding=\"async\" class=\"alignnone wp-image-1948 size-medium\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2025\/04\/Img2.png\" alt=\"\" width=\"700\" \/><\/p>\n<p>His work addressed the challenge of limited and imbalanced labeled datasets by leveraging contrastive learning with triplet networks to align multimodal data\u2014such as SAR and optical images\u2014in a shared latent space. Additionally, COMMANet enabled multimodal synthetic data generation, enhancing training in low-resource scenarios while maintaining consistent alignment across modalities.<\/p>\n<div style=\"text-align: center\">\n<table style=\"margin: auto\">\n<tbody>\n<tr>\n<td style=\"padding: 10px\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2025\/04\/Img1.png\" alt=\"3D scatter plot of land cover classes projected onto three principal components, showing clustered groups for forest, soil, residential, industrial, low plants, commercial, allotment, and water using HSI and SAR data, with each class represented by different colors and markers\" width=\"260\" height=\"524\" \/><\/td>\n<td style=\"padding: 10px\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2025\/04\/Img3-e1743963849441.png\" alt=\"Line graph titled \u2018Synthetic Grass\u2019 showing reflectance across spectral bands, comparing original data and multinomial distribution reconstruction, with both curves closely aligned across wavelengths\" width=\"380\" height=\"406\" \/><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><img decoding=\"async\" class=\"alignnone wp-image-1948 size-medium\" src=\"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-content\/uploads\/sites\/759\/2025\/04\/Img4.png\" alt=\"\" width=\"700\" \/><\/p>\n<p>This unified framework integrated both translation and classification tasks with a single model. We are excited to see more of your future achievements, Dr. Dutt!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Congratulations to Dr. Aditya Dutt for successfully passing his PhD dissertation exam! Dr. Dutt\u2019s research introduced the Contrastive MultiModal Alignment Network (COMMANet), a novel approach to shared manifold-based domain translation and fusion. His work addressed the challenge of limited and imbalanced labeled datasets by leveraging contrastive learning with triplet networks to align multimodal data\u2014such as [&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":[9],"tags":[161,177,223,227,247,483,485,551,761],"class_list":["post-13809","post","type-post","status-publish","format-standard","hentry","category-news","tag-commanet","tag-contrastive-learning","tag-deep-learning","tag-defense","tag-domain-translation","tag-multimodal-learning","tag-multimodal-triplet-autoencoder","tag-phd","tag-triplet-networks"],"acf":[],"_links":{"self":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/13809","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=13809"}],"version-history":[{"count":2,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/13809\/revisions"}],"predecessor-version":[{"id":16575,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/posts\/13809\/revisions\/16575"}],"wp:attachment":[{"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/media?parent=13809"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/categories?post=13809"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/faculty.eng.ufl.edu\/machine-learning\/wp-json\/wp\/v2\/tags?post=13809"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}