{"675217":{"#nid":"675217","#data":{"type":"event","title":"PhD Defense by Prithvijit Chattopadhyay","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E\u0026nbsp;Harnessing Synthetic Data for Robust and Reliable Vision\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E\u0026nbsp;July 2nd, 2024\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETime:\u003C\/strong\u003E\u0026nbsp;2:30pm - 4:30pm ET\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation:\u003C\/strong\u003E\u0026nbsp;CODA C1115 Druid Hills\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EZoom Link:\u003C\/strong\u003E\u0026nbsp;\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/96316092795\u0022 title=\u0022https:\/\/gatech.zoom.us\/j\/96316092795\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/96316092795\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EPrithvijit Chattopadhyay\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EComputer Science PhD Student\u003C\/p\u003E\u003Cp\u003EInteractive Computing\u003C\/p\u003E\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E\u003C\/p\u003E\u003Col type=\u00221\u0022\u003E\u003Cli\u003EJudy Hoffman (Advisor, IC, GT)\u003C\/li\u003E\u003Cli\u003EDhruv Batra (IC, GT)\u003C\/li\u003E\u003Cli\u003EJames Hays (IC, GT)\u003C\/li\u003E\u003Cli\u003EAnimesh Garg (IC, GT)\u003C\/li\u003E\u003Cli\u003ERoozbeh Mottaghi (Meta AI)\u003C\/li\u003E\u003C\/ol\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EProgress in computer vision has been driven by models trained on large amounts of exemplar data for different tasks. These exemplar data sources intend to capture task-specific information and instance-level variations that a trained model will likely encounter in the wild. However, for conditions where curating lots of labeled real-world data is prohibitively expensive, synthetic data can serve as a cost-effective alternative. Synthetic data sources offer a few key benefits: fast access to labeled task-specific data at scale, labels across varying task complexities, and curation of labeled data across diverse conditions in a controlled manner.\u003C\/p\u003E\u003Cp\u003EIn this thesis defense, I will focus on how \u201ccontrolled variations\u201d in synthetic data can be used to develop robust and reliable vision models. Controlled variations refer to intentional, systematic modifications to synthetic data, designed to either explore specific aspects of model behavior or improve model transfer across distributions. First, I will discuss RobustNav and SkyScenes, which apply controlled variations internally at the data-engine (simulator) stage to create diverse instances to systematically investigate the robustness of trained vision models. Next, I will discuss PASTA and AUGCAL, which apply controlled variations externally as data augmentations, guided by observed distributional discrepancies between synthetic and real data, to develop robust and reliable models.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EHarnessing Synthetic Data for Robust and Reliable Vision\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Harnessing Synthetic Data for Robust and Reliable Vision"}],"uid":"27707","created_gmt":"2024-06-24 20:15:45","changed_gmt":"2024-06-24 20:16:31","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-07-02T14:30:00-04:00","event_time_end":"2024-07-02T16:30:00-04:00","event_time_end_last":"2024-07-02T16:30:00-04:00","gmt_time_start":"2024-07-02 18:30:00","gmt_time_end":"2024-07-02 20:30:00","gmt_time_end_last":"2024-07-02 20:30:00","rrule":null,"timezone":"America\/New_York"},"location":"CODA C1115 Druid Hills","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":""}}}