{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_47916"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_47916","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"Towards interpretable face recognition","abstract":"Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models to visualize how they make predictions. Recent works further push the interpretability in the network learning stage to learn more meaningful representations. In this work, focusing on a specific area of visual recognition, we report our efforts towards interpretable face recognition. We propose a spatial activation diversity loss to learn more structured face representations. By leveraging the structure, we further design a feature activation diversity loss to push the interpretable representations to be discriminative and robust to occlusions. We demonstrate on three face recognition benchmarks that our proposed method is able to achieve the state-of-art face recognition accuracy with easily interpretable face representations.","abstract_html":"Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models to visualize how they make predictions. Recent works further push the interpretability in the network learning stage to learn more meaningful representations. In this work, focusing on a specific area of visual recognition, we report our efforts towards interpretable face recognition. We propose a spatial activation diversity loss to learn more structured face representations. By leveraging the structure, we further design a feature activation diversity loss to push the interpretable representations to be discriminative and robust to occlusions. We demonstrate on three face recognition benchmarks that our proposed method is able to achieve the state-of-art face recognition accuracy with easily interpretable face representations.","abstract_has_math":false,"creators":["Yin, Bangjie"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Liu, Xiaoming","Ross, Arun Abraham","Chai, Joyce Yue","Michigan State University"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019","date_published":"2019","updated_at":"2026-11-18T18:53:08Z","subjects":["Human face recognition (Computer science)"],"languages":["English"],"rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:47916","isbn:9781392176238","isbn:1392176239","oclc:1117774756","umi:13883404","local:Yin_grad.msu_0128N_16867"],"render_values":[{"text":"etd:47916","href":null,"code":true},{"text":"isbn:9781392176238","href":null,"code":true},{"text":"isbn:1392176239","href":null,"code":true},{"text":"oclc:1117774756","href":null,"code":true},{"text":"umi:13883404","href":null,"code":true},{"text":"local:Yin_grad.msu_0128N_16867","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/meg3-vb47","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/meg3-vb47","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_47916","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Liu, Xiaoming","Ross, Arun Abraham","Chai, Joyce Yue","Michigan State University"]},{"key":"dc:creator","label":"Author","values":["Yin, Bangjie"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["Text","Theses"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Human face recognition (Computer science)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial-ShareAlike 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:47916","isbn:9781392176238","isbn:1392176239","oclc:1117774756","umi:13883404","local:Yin_grad.msu_0128N_16867","https://doi.org/doi:10.25335/meg3-vb47"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models to visualize how they make predictions. Recent works further push the interpretability in the network learning stage to learn more meaningful representations. In this work, focusing on a specific area of visual recognition, we report our efforts towards interpretable face recognition. We propose a spatial activation diversity loss to learn more structured face representations. By leveraging the structure, we further design a feature activation diversity loss to push the interpretable representations to be discriminative and robust to occlusions. We demonstrate on three face recognition benchmarks that our proposed method is able to achieve the state-of-art face recognition accuracy with easily interpretable face representations.","Thesis (M.S.)--Michigan State University. Computer Science, 2019","Includes bibliographical references (pages 34-38)"]},{"key":"dc:format","label":"Dc Format","values":["ix, 38 pages","application/pdf"]},{"key":"dc:title","label":"Title","values":["Towards interpretable face recognition"]}]}],"canonical_facts":{"dc:contributor":["Liu, Xiaoming","Ross, Arun Abraham","Chai, Joyce Yue","Michigan State University"],"dc:creator":["Yin, Bangjie"],"dc:date":["2019"],"dc:description":["Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models to visualize how they make predictions. Recent works further push the interpretability in the network learning stage to learn more meaningful representations. In this work, focusing on a specific area of visual recognition, we report our efforts towards interpretable face recognition. We propose a spatial activation diversity loss to learn more structured face representations. By leveraging the structure, we further design a feature activation diversity loss to push the interpretable representations to be discriminative and robust to occlusions. We demonstrate on three face recognition benchmarks that our proposed method is able to achieve the state-of-art face recognition accuracy with easily interpretable face representations.","Thesis (M.S.)--Michigan State University. Computer Science, 2019","Includes bibliographical references (pages 34-38)"],"dc:format":["ix, 38 pages","application/pdf"],"dc:identifier":["etd:47916","isbn:9781392176238","isbn:1392176239","oclc:1117774756","umi:13883404","local:Yin_grad.msu_0128N_16867","https://doi.org/doi:10.25335/meg3-vb47"],"dc:language":["English"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["Attribution-NonCommercial-ShareAlike 4.0 International"],"dc:subject":["Human face recognition (Computer science)"],"dc:title":["Towards interpretable face recognition"],"dc:type":["Text","Theses"]},"updated_at":"2026-11-18T18:53:08Z"}