{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/124435"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/124435","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Stats-aware-GAN: Domain specific statistics matching in generative adversarial networks","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","abstract_has_math":false,"creators":["Kamath, Nidhish Ganesh"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Industrial Engineering","degree_department":null,"school":null,"contributors":["Lazebnik, Svetlana"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:25:00Z","subjects":["Generative Adversarial Networks","Distribution Matching In Gans","Domain Specific Statistics In Generative Modeling","Statistical Distributions In Generated Radiology Images","Gans","Generative Image Modeling","Computer Vision For Medical Images","Medical Image Generation"],"languages":["en","eng"],"rights":["Copyright 2024 Nidhish Ganesh Kamath"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/124435","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lazebnik, Svetlana"]},{"key":"dc:creator","label":"Author","values":["Kamath, Nidhish Ganesh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-05","2024-05-02"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Industrial Engineering"]},{"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":["Generative Adversarial Networks","Distribution Matching In Gans","Domain Specific Statistics In Generative Modeling","Statistical Distributions In Generated Radiology Images","Gans","Generative Image Modeling","Computer Vision For Medical Images","Medical Image Generation"]}]},{"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 2024 Nidhish Ganesh Kamath"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/124435"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","The student, Nidhish Kamath, accepted the attached license on 2024-04-29 at 17:37.","The student, Nidhish Kamath, submitted this Thesis for approval on 2024-04-29 at 17:59.","This Thesis was approved for publication on 2024-05-02 at 13:42.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20699 on 2024-09-16 at 00:37:24","State-of-the-art GANs such as StyleGAN2 have been regarded as being capable of mimicking a real data distribution and are able to produce photorealistic images when trained using large datasets of images such as faces of people, animals or natural scenes. However, in the case of images that are specific to a particular engineering domain like radiology or material science, StyleGAN2-generated images, though still seemingly realistic to the untrained eye, have been shown not to follow known distributions of key statistics specific to the domain. This non-adherence of important statistical distributions renders the generated images unsuitable for downstream tasks in that domain. Our work aims to find a way to bridge this gap, i.e., aid GANs (particularly StyleGAN2) in correctly modeling domain specific statistics in images. We study the use of various regularizing loss functions formulated with the goal of either improving distributional similarity or fooling a two sample test. Particularly, we explore using the Bhattacharyya distance and Kullback-Leibler divergence for measuring distributional similarity and smoothened formulations of the Friedman-Rafsky and k-Nearest Neighbor two sample tests, and report our findings."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Stats-aware-GAN: Domain specific statistics matching in generative adversarial networks"]}]}],"canonical_facts":{"dc:contributor":["Lazebnik, Svetlana"],"dc:creator":["Kamath, Nidhish Ganesh"],"dc:date":["2024-05","2024-05-02"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms","The student, Nidhish Kamath, accepted the attached license on 2024-04-29 at 17:37.","The student, Nidhish Kamath, submitted this Thesis for approval on 2024-04-29 at 17:59.","This Thesis was approved for publication on 2024-05-02 at 13:42.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20699 on 2024-09-16 at 00:37:24","State-of-the-art GANs such as StyleGAN2 have been regarded as being capable of mimicking a real data distribution and are able to produce photorealistic images when trained using large datasets of images such as faces of people, animals or natural scenes. However, in the case of images that are specific to a particular engineering domain like radiology or material science, StyleGAN2-generated images, though still seemingly realistic to the untrained eye, have been shown not to follow known distributions of key statistics specific to the domain. This non-adherence of important statistical distributions renders the generated images unsuitable for downstream tasks in that domain. Our work aims to find a way to bridge this gap, i.e., aid GANs (particularly StyleGAN2) in correctly modeling domain specific statistics in images. We study the use of various regularizing loss functions formulated with the goal of either improving distributional similarity or fooling a two sample test. Particularly, we explore using the Bhattacharyya distance and Kullback-Leibler divergence for measuring distributional similarity and smoothened formulations of the Friedman-Rafsky and k-Nearest Neighbor two sample tests, and report our findings."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/124435"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Nidhish Ganesh Kamath"],"dc:subject":["Generative Adversarial Networks","Distribution Matching In Gans","Domain Specific Statistics In Generative Modeling","Statistical Distributions In Generated Radiology Images","Gans","Generative Image Modeling","Computer Vision For Medical Images","Medical Image Generation"],"dc:title":["Stats-aware-GAN: Domain specific statistics matching in generative adversarial networks"],"dc:type":["text"],"thesis:degree_discipline":["Industrial Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:00Z"}