{"670909":{"#nid":"670909","#data":{"type":"event","title":"PhD Defense by Viraj Prabhu","body":[{"value":"\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cstrong\u003E\u003Cspan\u003E\u003Cspan\u003ETitle\u003C\/span\u003E\u003C\/span\u003E\u003C\/strong\u003E\u003Cspan\u003E\u003Cspan\u003E: Towards Reliable Computer Vision Systems\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cstrong\u003E\u003Cspan\u003E\u003Cspan\u003EDate\u003C\/span\u003E\u003C\/span\u003E\u003C\/strong\u003E\u003Cspan\u003E\u003Cspan\u003E: Monday, November 20, 2023\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cstrong\u003E\u003Cspan\u003E\u003Cspan\u003ETime\u003C\/span\u003E\u003C\/span\u003E\u003C\/strong\u003E\u003Cspan\u003E\u003Cspan\u003E: 4:00-6:00pm (ET)\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cstrong\u003E\u003Cspan\u003E\u003Cspan\u003ELocation: \u003C\/span\u003E\u003C\/span\u003E\u003C\/strong\u003E\u003Cspan\u003E\u003Cspan\u003ECODA C1115 (Druid Hills) \u0026amp; \u003C\/span\u003E\u003C\/span\u003E\u003Cspan\u003E\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/92801380802?pwd=N3VWNXBRSGYyckVaRWlXaWVwSnZEdz09\u0026amp;from=addon\u0022\u003E\u003Cspan\u003EZoom\u003C\/span\u003E\u003C\/a\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cstrong\u003E\u003Cspan\u003E\u003Cspan\u003EViraj Prabhu\u003C\/span\u003E\u003C\/span\u003E\u003C\/strong\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EPhD student in Computer Science\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003ESchool of Interactive Computing\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EGeorgia Institute of Technology\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u0026nbsp;\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cstrong\u003E\u003Cspan\u003E\u003Cspan\u003ECommittee\u003C\/span\u003E\u003C\/span\u003E\u003C\/strong\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EDr. Judy Hoffman (advisor), School of Interactive Computing, Georgia Institute of Technology\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EDr. Dhruv Batra, School of Interactive Computing, Georgia Institute of Technology \u0026amp; Meta\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EDr. James Hays, School of Interactive Computing, Georgia Institute of Technology\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EDr. Zsolt Kira, School of Interactive Computing, Georgia Institute of Technology\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EDr. Sanja Fidler, University of Toronto \u0026amp; NVIDIA\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cstrong\u003E\u003Cspan\u003E\u003Cspan\u003EAbstract\u003C\/span\u003E\u003C\/span\u003E\u003C\/strong\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EThe real world has infinite visual variation \u2013 across viewpoints, time, space, and curation. As deep visual models become ubiquitous in high-stakes applications, their ability to generalize across such variation becomes increasingly important. Such generalization will alleviate the need to label a large corpus for every new deployment, which may be infeasible due to data volume (e.g., autonomous driving) or labeling cost (e.g., medical diagnosis). Further, it is necessary to overcome the natural spatiotemporal distribution shifts that a deployed model will invariably face (e.g., changing geographies and seasons). Finally, such generalization will unlock the possibility of knowledge transfer from inexpensive sources of data (e.g., transferring models trained in simulation to reality).\u0026nbsp;\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cbr \/\u003E\r\n\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003EIn this thesis, I will present opportunities to improve such generalization at different stages of the ML lifecycle. First, I will discuss \u003Cem\u003Eproactive\u003C\/em\u003E strategies for training robust models by leveraging simulation to augment the long tail of real training data. Next, I will present \u003Cem\u003Ereactive\u003C\/em\u003E strategies to recover from unforeseen distribution shifts via self-supervised domain adaptation. Finally, I will present a framework to \u003Cem\u003Estress-test \u003C\/em\u003Ethe robustness of vision models by leveraging foundation models for text and image synthesis to generate challenging counterfactual test cases.\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u0026nbsp;Towards Reliable Computer Vision Systems\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":" Towards Reliable Computer Vision Systems"}],"uid":"27707","created_gmt":"2023-11-06 20:34:42","changed_gmt":"2023-11-14 18:51:08","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2023-11-20T16:00:00-05:00","event_time_end":"2023-11-20T18:00:00-05:00","event_time_end_last":"2023-11-20T18:00:00-05:00","gmt_time_start":"2023-11-20 21:00:00","gmt_time_end":"2023-11-20 23:00:00","gmt_time_end_last":"2023-11-20 23:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Coda C1115 and Zoom","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}