{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/117596"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/117596","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Efficient mining of informative descriptors from data with scarce annotations","abstract":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2024-12-01","abstract_html":"Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2024-12-01","abstract_has_math":false,"creators":["Zhuang, Furen"],"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":["Moulin, Pierre","Veeravalli, Venugopal V","Schwing, Alexander G","Wang, Yuxiong"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-12","date_published":"2022-12","updated_at":"2026-07-22T22:24:56Z","subjects":["Metric Learning","Retrieval","Hashing"],"languages":["en","eng"],"rights":["Copyright 2022 Furen Zhuang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/117596","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Moulin, Pierre","Veeravalli, Venugopal V","Schwing, Alexander G","Wang, Yuxiong"]},{"key":"dc:creator","label":"Author","values":["Zhuang, Furen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-12","2022-12-02"]},{"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":["Metric Learning","Retrieval","Hashing"]}]},{"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 2022 Furen Zhuang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/117596"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2024-12-01","The student, Furen Zhuang, accepted the attached license on 2022-12-02 at 00:38.","The student, Furen Zhuang, submitted this Dissertation for approval on 2022-12-02 at 00:54.","This Dissertation was approved for publication on 2022-12-02 at 09:27.","DSpace SAF Submission Ingestion Package generated from Vireo submission #18733 on 2023-04-12 at 11:36:50","In this thesis informative descriptors are learnt where similar data are closer than dissimilar ones. Such descriptors are commonly used in Content-Based Information Retrieval applications, where the amount of data that needs to be handled is very large. To that end, it is ideal for the descriptors to be compact, the training method able to effectively utilize scarce annotations, and the representations able to generalize to unseen data. The second chapter shows how very short hash codes can be learnt which perform well in image retrieval. It is desired for such hash codes to be similarity-preserving, balanced and pairwise uncorrelated. Similarity-preserving means the hash codes of similar images have a shorter Hamming distance than dissimilar ones. Balanced bits means each bit coordinate has uniform probability. Balanced and uncorrelated bits encourage an equal number of data items to be mapped to each code. We utilize a variational autoencoder (VAE) and show how all three ideals can be seamlessly incorporated into the VAE to directly obtain hash bits from an intermediate layer. We also extend the framework to improve generalizability, allowing the hash codes to perform well even on classes that were unseen during training. This is achieved by explicitly tolerating variation found in the hash codes of similar data, while ensuring that label-consistency is maintained. The third chapter proposes a semi-supervised metric learning method which is computationally efficient due to the use of proxies and is able to effectively harness unlabeled data by identifying far-apart similar pairs and close dissimilar pairs. In the fourth chapter, we show how this identification can be improved using the provided labels. A new mixed label propagation method is also proposed to incorporate negative edge information into label propagation."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Efficient mining of informative descriptors from data with scarce annotations"]}]}],"canonical_facts":{"dc:contributor":["Moulin, Pierre","Veeravalli, Venugopal V","Schwing, Alexander G","Wang, Yuxiong"],"dc:creator":["Zhuang, Furen"],"dc:date":["2022-12","2022-12-02"],"dc:description":["Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2024-12-01","The student, Furen Zhuang, accepted the attached license on 2022-12-02 at 00:38.","The student, Furen Zhuang, submitted this Dissertation for approval on 2022-12-02 at 00:54.","This Dissertation was approved for publication on 2022-12-02 at 09:27.","DSpace SAF Submission Ingestion Package generated from Vireo submission #18733 on 2023-04-12 at 11:36:50","In this thesis informative descriptors are learnt where similar data are closer than dissimilar ones. Such descriptors are commonly used in Content-Based Information Retrieval applications, where the amount of data that needs to be handled is very large. To that end, it is ideal for the descriptors to be compact, the training method able to effectively utilize scarce annotations, and the representations able to generalize to unseen data. The second chapter shows how very short hash codes can be learnt which perform well in image retrieval. It is desired for such hash codes to be similarity-preserving, balanced and pairwise uncorrelated. Similarity-preserving means the hash codes of similar images have a shorter Hamming distance than dissimilar ones. Balanced bits means each bit coordinate has uniform probability. Balanced and uncorrelated bits encourage an equal number of data items to be mapped to each code. We utilize a variational autoencoder (VAE) and show how all three ideals can be seamlessly incorporated into the VAE to directly obtain hash bits from an intermediate layer. We also extend the framework to improve generalizability, allowing the hash codes to perform well even on classes that were unseen during training. This is achieved by explicitly tolerating variation found in the hash codes of similar data, while ensuring that label-consistency is maintained. The third chapter proposes a semi-supervised metric learning method which is computationally efficient due to the use of proxies and is able to effectively harness unlabeled data by identifying far-apart similar pairs and close dissimilar pairs. In the fourth chapter, we show how this identification can be improved using the provided labels. A new mixed label propagation method is also proposed to incorporate negative edge information into label propagation."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/117596"],"dc:language":["en","eng"],"dc:rights":["Copyright 2022 Furen Zhuang"],"dc:subject":["Metric Learning","Retrieval","Hashing"],"dc:title":["Efficient mining of informative descriptors from data with scarce annotations"],"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":"2026-07-22T22:24:56Z"}