{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/120318"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/120318","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Measuring the robustness and generalization properties of unified vision and language models","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","abstract_has_math":false,"creators":["Marten, Ryan Lewis"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Hoiem, Derek"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-05","date_published":"2023-05","updated_at":"2026-07-22T22:24:57Z","subjects":["Ai","Computer Vision","Benchmark"],"languages":["en","eng"],"rights":["Copyright 2023 Ryan Marten"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/120318","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hoiem, Derek"]},{"key":"dc:creator","label":"Author","values":["Marten, Ryan Lewis"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-05","2023-04-24"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Ai","Computer Vision","Benchmark"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2023 Ryan Marten"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/120318"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","The student, Ryan Marten, accepted the attached license on 2023-04-22 at 09:11.","The student, Ryan Marten, submitted this Thesis for approval on 2023-04-22 at 09:16.","This Thesis was approved for publication on 2023-04-24 at 11:07.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19112 on 2023-09-01 at 17:09:26","Computer vision models excel at making predictions when the test distribution closely resembles the training distribution. Such models have yet to match the ability of biological vision to learn from multiple sources and generalize to new data sources and tasks. To facilitate the development and evaluation of more general vision systems, we introduce the General Robust Image Task (GRIT) benchmark. GRIT evaluates the performance, robustness, and calibration of a vision system across a variety of image prediction tasks, concepts, and data sources. The seven tasks in GRIT are selected to cover a range of visual skills: object categorization, object localization, referring expression grounding, visual question answering, segmentation, human keypoint detection, and surface normal estimation. GRIT is carefully designed to enable the evaluation of robustness under image perturbations, image source distribution shift, and concept distribution shift. By providing a unified platform for thorough assessment of skills and concepts learned by a vision model, we hope GRIT catalyzes the development of performant and robust general purpose vision systems."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Measuring the robustness and generalization properties of unified vision and language models"]}]}],"canonical_facts":{"dc:contributor":["Hoiem, Derek"],"dc:creator":["Marten, Ryan Lewis"],"dc:date":["2023-05","2023-04-24"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms","The student, Ryan Marten, accepted the attached license on 2023-04-22 at 09:11.","The student, Ryan Marten, submitted this Thesis for approval on 2023-04-22 at 09:16.","This Thesis was approved for publication on 2023-04-24 at 11:07.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19112 on 2023-09-01 at 17:09:26","Computer vision models excel at making predictions when the test distribution closely resembles the training distribution. Such models have yet to match the ability of biological vision to learn from multiple sources and generalize to new data sources and tasks. To facilitate the development and evaluation of more general vision systems, we introduce the General Robust Image Task (GRIT) benchmark. GRIT evaluates the performance, robustness, and calibration of a vision system across a variety of image prediction tasks, concepts, and data sources. The seven tasks in GRIT are selected to cover a range of visual skills: object categorization, object localization, referring expression grounding, visual question answering, segmentation, human keypoint detection, and surface normal estimation. GRIT is carefully designed to enable the evaluation of robustness under image perturbations, image source distribution shift, and concept distribution shift. By providing a unified platform for thorough assessment of skills and concepts learned by a vision model, we hope GRIT catalyzes the development of performant and robust general purpose vision systems."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/120318"],"dc:language":["en","eng"],"dc:rights":["Copyright 2023 Ryan Marten"],"dc:subject":["Ai","Computer Vision","Benchmark"],"dc:title":["Measuring the robustness and generalization properties of unified vision and language models"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:57Z"}