{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/102792"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/102792","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Novel feature construction technique for detecting anomalous faces and evaluating style transfer methods","abstract":"In this thesis, we focus on how careful design and evaluation of deep-learned features are still necessary like hand-crafted features for computer vision tasks. We demonstrate this in two different domain problems – Anomaly Detection and Style Transfer. We present feature aggregation techniques and also quantitative evaluation procedure for these tasks. For anomaly detection, we propose a novel facial anomaly detection task, where we demonstrate a feature extraction procedure using a specially trained autoencoder for detecting anomalous faces without seeing any example anomalies during training. We built a new dataset of anomalous faces and typical faces for evaluating the proposed framework that beats many standard baselines. For style transfer, we developed the first quantitative evaluation procedure for evaluating existing style transfer methods using an effectiveness and coherence metric to measure how effectively a style has transferred without distorting object boundaries much. Doing so, helped us to design better features for extracting style using cross-layer gram matrices instead of popularly adopted within later gram matrices. Both works signify understanding features and their careful design are still crucial in building state of the art computer vision algorithms.","abstract_html":"In this thesis, we focus on how careful design and evaluation of deep-learned features are still necessary like hand-crafted features for computer vision tasks. We demonstrate this in two different domain problems – Anomaly Detection and Style Transfer. We present feature aggregation techniques and also quantitative evaluation procedure for these tasks. For anomaly detection, we propose a novel facial anomaly detection task, where we demonstrate a feature extraction procedure using a specially trained autoencoder for detecting anomalous faces without seeing any example anomalies during training. We built a new dataset of anomalous faces and typical faces for evaluating the proposed framework that beats many standard baselines. For style transfer, we developed the first quantitative evaluation procedure for evaluating existing style transfer methods using an effectiveness and coherence metric to measure how effectively a style has transferred without distorting object boundaries much. Doing so, helped us to design better features for extracting style using cross-layer gram matrices instead of popularly adopted within later gram matrices. Both works signify understanding features and their careful design are still crucial in building state of the art computer vision algorithms.","abstract_has_math":false,"creators":["Bhattad, Anand"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Forsyth, David A."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-02-07T20:35:57Z","date_published":"2019-02-07T20:35:57Z","updated_at":"2026-07-22T22:24:42Z","subjects":["Feature Extraction, Quantitative Evaluation of Features, Face Anomaly Detection, Style Transfer"],"languages":["en"],"rights":["Copyright 2018 Anand Bhattad"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/102792","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Forsyth, David A."]},{"key":"dc:creator","label":"Author","values":["Bhattad, Anand"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-02-07T20:35:57Z","2021-02-08T10:15:11Z","2018-11-09","2018-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"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":["Feature Extraction, Quantitative Evaluation of Features, Face Anomaly Detection, Style Transfer"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2018 Anand Bhattad"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/102792"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In this thesis, we focus on how careful design and evaluation of deep-learned features are still necessary like hand-crafted features for computer vision tasks. We demonstrate this in two different domain problems – Anomaly Detection and Style Transfer. We present feature aggregation techniques and also quantitative evaluation procedure for these tasks. For anomaly detection, we propose a novel facial anomaly detection task, where we demonstrate a feature extraction procedure using a specially trained autoencoder for detecting anomalous faces without seeing any example anomalies during training. We built a new dataset of anomalous faces and typical faces for evaluating the proposed framework that beats many standard baselines. For style transfer, we developed the first quantitative evaluation procedure for evaluating existing style transfer methods using an effectiveness and coherence metric to measure how effectively a style has transferred without distorting object boundaries much. Doing so, helped us to design better features for extracting style using cross-layer gram matrices instead of popularly adopted within later gram matrices. Both works signify understanding features and their careful design are still crucial in building state of the art computer vision algorithms.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-12-01","The student, Anand Bhattad, accepted the attached license on 2018-11-07 at 15:55.","The student, Anand Bhattad, submitted this Thesis for approval on 2018-11-07 at 16:06.","This Thesis was approved for publication on 2018-11-09 at 10:37.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13070 on 2019-02-07 at 14:17:11","Made available in DSpace on 2019-02-07T20:35:57Z (GMT). No. of bitstreams: 2 BHATTAD-THESIS-2018.pdf: 63504759 bytes, checksum: 5bc3416f2c0a7a2ca0de14d1e89a84aa (MD5) LICENSE.txt: 4210 bytes, checksum: 8c36a559eea0d493b2b1fb748c41f183 (MD5) Previous issue date: 2018-11-09","Embargo set by: Seth Robbins for item 109816 Lift date: 2021-02-07T20:36:09Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 109816 Lift date: 2021-02-07T20:39:46Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 109816 Lift date: 2021-02-07T20:44:35Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 109816 on 2021-02-08T10:15:11Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Novel feature construction technique for detecting anomalous faces and evaluating style transfer methods"]}]}],"canonical_facts":{"dc:contributor":["Forsyth, David A."],"dc:creator":["Bhattad, Anand"],"dc:date":["2019-02-07T20:35:57Z","2021-02-08T10:15:11Z","2018-11-09","2018-12"],"dc:description":["In this thesis, we focus on how careful design and evaluation of deep-learned features are still necessary like hand-crafted features for computer vision tasks. We demonstrate this in two different domain problems – Anomaly Detection and Style Transfer. We present feature aggregation techniques and also quantitative evaluation procedure for these tasks. For anomaly detection, we propose a novel facial anomaly detection task, where we demonstrate a feature extraction procedure using a specially trained autoencoder for detecting anomalous faces without seeing any example anomalies during training. We built a new dataset of anomalous faces and typical faces for evaluating the proposed framework that beats many standard baselines. For style transfer, we developed the first quantitative evaluation procedure for evaluating existing style transfer methods using an effectiveness and coherence metric to measure how effectively a style has transferred without distorting object boundaries much. Doing so, helped us to design better features for extracting style using cross-layer gram matrices instead of popularly adopted within later gram matrices. Both works signify understanding features and their careful design are still crucial in building state of the art computer vision algorithms.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-12-01","The student, Anand Bhattad, accepted the attached license on 2018-11-07 at 15:55.","The student, Anand Bhattad, submitted this Thesis for approval on 2018-11-07 at 16:06.","This Thesis was approved for publication on 2018-11-09 at 10:37.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13070 on 2019-02-07 at 14:17:11","Made available in DSpace on 2019-02-07T20:35:57Z (GMT). No. of bitstreams: 2 BHATTAD-THESIS-2018.pdf: 63504759 bytes, checksum: 5bc3416f2c0a7a2ca0de14d1e89a84aa (MD5) LICENSE.txt: 4210 bytes, checksum: 8c36a559eea0d493b2b1fb748c41f183 (MD5) Previous issue date: 2018-11-09","Embargo set by: Seth Robbins for item 109816 Lift date: 2021-02-07T20:36:09Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 109816 Lift date: 2021-02-07T20:39:46Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 109816 Lift date: 2021-02-07T20:44:35Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 109816 on 2021-02-08T10:15:11Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/102792"],"dc:language":["en"],"dc:rights":["Copyright 2018 Anand Bhattad"],"dc:subject":["Feature Extraction, Quantitative Evaluation of Features, Face Anomaly Detection, Style Transfer"],"dc:title":["Novel feature construction technique for detecting anomalous faces and evaluating style transfer methods"],"dc:type":["text"],"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":"2026-07-22T22:24:42Z"}