{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/114008"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/114008","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Sparse representation in deep vision models","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-12-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-12-01","abstract_has_math":false,"creators":["Fan, Yuchen"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Hasegawa-Johnson, Mark","Liang, Zhi-Pei","Smaragdis, Paris","Shi, Humphrey"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-04-29T21:46:19Z","date_published":"2022-04-29T21:46:19Z","updated_at":"2026-07-22T22:24:54Z","subjects":["Engineering"],"languages":["en","eng"],"rights":["Copyright 2021 Yuchen Fan"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/114008","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hasegawa-Johnson, Mark","Liang, Zhi-Pei","Smaragdis, Paris","Shi, Humphrey"]},{"key":"dc:creator","label":"Author","values":["Fan, Yuchen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-04-29T21:46:19Z","2024-04-29T21:47:53Z","2021-12","2021-12-03"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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":["Engineering"]}]},{"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 2021 Yuchen Fan"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/114008"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-12-01","The student, Yuchen Fan, accepted the attached license on 2021-12-03 at 15:51.","The student, Yuchen Fan, submitted this Dissertation for approval on 2021-12-03 at 15:58.","This Dissertation was approved for publication on 2021-12-03 at 16:06.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17388 on 2022-04-06 at 17:17:54","Made available in DSpace on 2022-04-29T21:46:19Z (GMT). No. of bitstreams: 2 FAN-DISSERTATION-2021.pdf: 23112467 bytes, checksum: 10ae4564d95daaf3403fff12b691fff5 (MD5) LICENSE.txt: 4207 bytes, checksum: 63a1016f898c9d10791c03607d295e8b (MD5) Previous issue date: 2021-12-03","Embargo set by: Seth Robbins for item 123372 Lift date: 2024-04-29T21:46:25Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 123372 Lift date: 2024-04-29T21:47:53Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only","Sparse representation plays a critical role in vision problems, including generation and understanding. Image generation tasks are inherently ill-posed, where the input signal usually has insufficient information while the output has infinitely many solutions w.r.t. the same input. Thus, it is commonly believed that sparse representation is more robust to handle the considerable diversity of solutions. Image understanding also depends on invariant and robust sparse representation for various transformations, e.g., color, lighting, viewpoint, etc. Deep neural networks extend the sparse coding-based methods from linear structure to cascaded linear and non-linear structures. However, sparsity of hidden representation in deep neural networks cannot be solved by iterative optimization as sparse coding, since deep networks are feed-forward during inference. I invented a method that can structurally enforce sparsity constraints upon hidden neurons in deep networks but also keep representation in high dimensionality. Given high-dimensional neurons, I divide them into groups along channels and allow only one group of neurons to be non-zero each time. The adaptive selection of the non-sparse group is modeled by tiny side networks upon context features. And computation is also saved when only performed on the non-zero group. I further extended the sparse constraints to an attention mechanism. Attention mechanism is built upon paired correlation between any two pixels and needs quadratic computation cost respecting to the input size. This mutual correlation is inherently sparse, since pixels in a single image are not necessary highly correlated to most of other pixels. I proposed a method to achieve more efficient computation of attention mechanism given the sparse prior of correlation matrix. I also investigated the sparse scene representation modeled with deep neural networks. With sparsely rendered views of a 3D scene, the proposed deep neural network approach performs spatiotemporal reconstruction of high-definition images from a novel viewpoint efficiently."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Sparse representation in deep vision models"]}]}],"canonical_facts":{"dc:contributor":["Hasegawa-Johnson, Mark","Liang, Zhi-Pei","Smaragdis, Paris","Shi, Humphrey"],"dc:creator":["Fan, Yuchen"],"dc:date":["2022-04-29T21:46:19Z","2024-04-29T21:47:53Z","2021-12","2021-12-03"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-12-01","The student, Yuchen Fan, accepted the attached license on 2021-12-03 at 15:51.","The student, Yuchen Fan, submitted this Dissertation for approval on 2021-12-03 at 15:58.","This Dissertation was approved for publication on 2021-12-03 at 16:06.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17388 on 2022-04-06 at 17:17:54","Made available in DSpace on 2022-04-29T21:46:19Z (GMT). No. of bitstreams: 2 FAN-DISSERTATION-2021.pdf: 23112467 bytes, checksum: 10ae4564d95daaf3403fff12b691fff5 (MD5) LICENSE.txt: 4207 bytes, checksum: 63a1016f898c9d10791c03607d295e8b (MD5) Previous issue date: 2021-12-03","Embargo set by: Seth Robbins for item 123372 Lift date: 2024-04-29T21:46:25Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 123372 Lift date: 2024-04-29T21:47:53Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only","Sparse representation plays a critical role in vision problems, including generation and understanding. Image generation tasks are inherently ill-posed, where the input signal usually has insufficient information while the output has infinitely many solutions w.r.t. the same input. Thus, it is commonly believed that sparse representation is more robust to handle the considerable diversity of solutions. Image understanding also depends on invariant and robust sparse representation for various transformations, e.g., color, lighting, viewpoint, etc. Deep neural networks extend the sparse coding-based methods from linear structure to cascaded linear and non-linear structures. However, sparsity of hidden representation in deep neural networks cannot be solved by iterative optimization as sparse coding, since deep networks are feed-forward during inference. I invented a method that can structurally enforce sparsity constraints upon hidden neurons in deep networks but also keep representation in high dimensionality. Given high-dimensional neurons, I divide them into groups along channels and allow only one group of neurons to be non-zero each time. The adaptive selection of the non-sparse group is modeled by tiny side networks upon context features. And computation is also saved when only performed on the non-zero group. I further extended the sparse constraints to an attention mechanism. Attention mechanism is built upon paired correlation between any two pixels and needs quadratic computation cost respecting to the input size. This mutual correlation is inherently sparse, since pixels in a single image are not necessary highly correlated to most of other pixels. I proposed a method to achieve more efficient computation of attention mechanism given the sparse prior of correlation matrix. I also investigated the sparse scene representation modeled with deep neural networks. With sparsely rendered views of a 3D scene, the proposed deep neural network approach performs spatiotemporal reconstruction of high-definition images from a novel viewpoint efficiently."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/114008"],"dc:language":["en","eng"],"dc:rights":["Copyright 2021 Yuchen Fan"],"dc:subject":["Engineering"],"dc:title":["Sparse representation in deep vision models"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:54Z"}