{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/128342"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/128342","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Learning distributions of transformations from small datasets for applied image synthesis","abstract":"Much of the recent research in machine learning and computer vision focuses on applications with large labeled datasets. However, in realistic settings, it is much more common to work with limited data. In this thesis, we investigate two applications of image synthesis using small datasets. First, we demonstrate how to use image synthesis to perform data augmentation, enabling the use of supervised learning methods with limited labeled data. Data augmentation -- typically the application of simple, hand-designed transformations such as rotation and scaling -- is often used to expand small datasets. We present a method for learning complex data augmentation transformations, producing examples that are more diverse, realistic, and useful for training supervised systems than hand-engineered augmentation. We demonstrate our proposed augmentation method for improving few-shot object classification performance, using a new dataset of collectible cards with fine-grained differences. We also apply our method to medical image segmentation, enabling the training of a supervised segmentation system using just a single labeled example. In our second application, we present a novel image synthesis task: synthesizing time lapse videos of the creation of digital and watercolor paintings. Using a recurrent model of paint strokes and a novel training scheme, we create videos that tell a plausible visual story of the painting process.","abstract_html":"Much of the recent research in machine learning and computer vision focuses on applications with large labeled datasets. However, in realistic settings, it is much more common to work with limited data. In this thesis, we investigate two applications of image synthesis using small datasets. First, we demonstrate how to use image synthesis to perform data augmentation, enabling the use of supervised learning methods with limited labeled data. Data augmentation -- typically the application of simple, hand-designed transformations such as rotation and scaling -- is often used to expand small datasets. We present a method for learning complex data augmentation transformations, producing examples that are more diverse, realistic, and useful for training supervised systems than hand-engineered augmentation. We demonstrate our proposed augmentation method for improving few-shot object classification performance, using a new dataset of collectible cards with fine-grained differences. We also apply our method to medical image segmentation, enabling the training of a supervised segmentation system using just a single labeled example. In our second application, we present a novel image synthesis task: synthesizing time lapse videos of the creation of digital and watercolor paintings. Using a recurrent model of paint strokes and a novel training scheme, we create videos that tell a plausible visual story of the painting process.","abstract_has_math":false,"creators":["Zhao, Amy(Xiaoyu Amy)"],"institution":"Massachusetts Institute of Technology","degree_name":"Doctoral","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["John V. Guttag, Frédo Durand and Adrian V. Dalca."],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020","date_published":"2020","updated_at":"2026-07-22T22:22:13Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/128342","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["John V. Guttag, Frédo Durand and Adrian V. Dalca."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Zhao, Amy(Xiaoyu Amy)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-11-03T20:31:55Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-11-03T20:31:55Z"]},{"key":"dc:date.issued","label":"Date","values":["2020"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctoral"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/128342"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2020","Cataloged from PDF of thesis. \"February 2020.\"","Includes bibliographical references (pages 75-91)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Much of the recent research in machine learning and computer vision focuses on applications with large labeled datasets. However, in realistic settings, it is much more common to work with limited data. In this thesis, we investigate two applications of image synthesis using small datasets. First, we demonstrate how to use image synthesis to perform data augmentation, enabling the use of supervised learning methods with limited labeled data. Data augmentation -- typically the application of simple, hand-designed transformations such as rotation and scaling -- is often used to expand small datasets. We present a method for learning complex data augmentation transformations, producing examples that are more diverse, realistic, and useful for training supervised systems than hand-engineered augmentation. We demonstrate our proposed augmentation method for improving few-shot object classification performance, using a new dataset of collectible cards with fine-grained differences. We also apply our method to medical image segmentation, enabling the training of a supervised segmentation system using just a single labeled example. In our second application, we present a novel image synthesis task: synthesizing time lapse videos of the creation of digital and watercolor paintings. Using a recurrent model of paint strokes and a novel training scheme, we create videos that tell a plausible visual story of the painting process."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph. D."]},{"key":"dc:title","label":"Title","values":["Learning distributions of transformations from small datasets for applied image synthesis"]}]}],"canonical_facts":{"dc:contributor.advisor":["John V. Guttag, Frédo Durand and Adrian V. Dalca."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Zhao, Amy(Xiaoyu Amy)"],"dc:date.accessioned":["2020-11-03T20:31:55Z"],"dc:date.available":["2020-11-03T20:31:55Z"],"dc:date.issued":["2020"],"dc:description":["Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2020","Cataloged from PDF of thesis. \"February 2020.\"","Includes bibliographical references (pages 75-91)."],"dc:description.abstract":["Much of the recent research in machine learning and computer vision focuses on applications with large labeled datasets. However, in realistic settings, it is much more common to work with limited data. In this thesis, we investigate two applications of image synthesis using small datasets. First, we demonstrate how to use image synthesis to perform data augmentation, enabling the use of supervised learning methods with limited labeled data. Data augmentation -- typically the application of simple, hand-designed transformations such as rotation and scaling -- is often used to expand small datasets. We present a method for learning complex data augmentation transformations, producing examples that are more diverse, realistic, and useful for training supervised systems than hand-engineered augmentation. We demonstrate our proposed augmentation method for improving few-shot object classification performance, using a new dataset of collectible cards with fine-grained differences. We also apply our method to medical image segmentation, enabling the training of a supervised segmentation system using just a single labeled example. In our second application, we present a novel image synthesis task: synthesizing time lapse videos of the creation of digital and watercolor paintings. Using a recurrent model of paint strokes and a novel training scheme, we create videos that tell a plausible visual story of the painting process."],"dc:description.degree":["Ph. D."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/128342"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Learning distributions of transformations from small datasets for applied image synthesis"],"dc:type":["Thesis"],"thesis:degree_name":["Doctoral"]},"updated_at":"2026-07-22T22:22:13Z"}