{"id":{"repo_id":"uwo","oai_identifier":"oai:uwo.scholaris.ca:20.500.14721/30050"},"canonical_url":"https://search.dev.ndltd.org/etd/uwo/oai:uwo.scholaris.ca:20.500.14721/30050","repository":{"repo_id":"uwo","name":"Western University","base_url":"https://uwo.scholaris.ca/server/oai/request"},"display":{"title":"A Patch-as-Filter Method for Same-Different Problems with Few-Shot Learning","abstract":"Convolutional Neural Network (CNN) has undergone tremendous advancements in recent years, but visual reasoning tasks are still a huge undertaking, particularly in few-shot learning cases. Little is known, especially in solving the Same-Different (SD) task, which is a type of visual reasoning task that requires seeking pattern repetitions in a single image. In this thesis, we propose a patch-as-filter method focusing on solving the SD tasks with few-shot learning. Firstly, a patch in an individual image is detected. Then, transformations are learned to create sample-specific convolutional filters. After applying these filters on the original input images, we, lastly, acquire feature maps indicating the duplicate segments. We show experimentally that our approach achieves the state-of-the-art few-shot performance on the Synthetic Visual Reasoning Test (SVRT) SD tasks by accuracy going up above 30% on average, with only ten training samples. Besides that, to further evaluate the effectiveness of our approach, SVRT-like tasks are generated with more difficult visual reasoning concepts. The results suggest that the average accuracy is increased by approximately 10% compared to several popular few-shot algorithms. The method we suggest here has shed new light upon new CNN approaches in solving the SD tasks with few-shot learning.","abstract_html":"Convolutional Neural Network (CNN) has undergone tremendous advancements in recent years, but visual reasoning tasks are still a huge undertaking, particularly in few-shot learning cases. Little is known, especially in solving the Same-Different (SD) task, which is a type of visual reasoning task that requires seeking pattern repetitions in a single image. In this thesis, we propose a patch-as-filter method focusing on solving the SD tasks with few-shot learning. Firstly, a patch in an individual image is detected. Then, transformations are learned to create sample-specific convolutional filters. After applying these filters on the original input images, we, lastly, acquire feature maps indicating the duplicate segments. We show experimentally that our approach achieves the state-of-the-art few-shot performance on the Synthetic Visual Reasoning Test (SVRT) SD tasks by accuracy going up above 30% on average, with only ten training samples. Besides that, to further evaluate the effectiveness of our approach, SVRT-like tasks are generated with more difficult visual reasoning concepts. The results suggest that the average accuracy is increased by approximately 10% compared to several popular few-shot algorithms. The method we suggest here has shed new light upon new CNN approaches in solving the SD tasks with few-shot learning.","abstract_has_math":false,"creators":["Hu, Yining"],"institution":"The University of Western Ontario","degree_name":"M Sc","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Ling, Charles"],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-04-24","date_published":"2020-04-24","updated_at":"2026-07-27T21:56:14Z","subjects":["Visual reasoning","Few-shot learning","Dynamic filters","Convolutional Neural Network"],"languages":["en_ca"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14721/30050","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Ling, Charles"]},{"key":"dc:creator","label":"Author","values":["Hu, Yining"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-07-10T18:36:39Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-07-10T18:36:39Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-04-24"]},{"key":"dc:publisher","label":"Institution","values":["The University of Western Ontario"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M Sc"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Visual reasoning","Few-shot learning","Dynamic filters","Convolutional Neural Network"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_ca"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14721/30050"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The thesis cover page in the PDF document includes references to Western University’s previous institutional repository platform, known as Scholarship@Western, and links to that platform (beginning with ir.lib.uwo.ca). In citing or referring to this thesis, use the DOI or handle from this page instead. Sample citation: Author name, \"Thesis title.\" (Year). Western University Open Repository. https://doi.org/10.71858/123456."]},{"key":"dc:description.abstract","label":"Abstract","values":["Convolutional Neural Network (CNN) has undergone tremendous advancements in recent years, but visual reasoning tasks are still a huge undertaking, particularly in few-shot learning cases. Little is known, especially in solving the Same-Different (SD) task, which is a type of visual reasoning task that requires seeking pattern repetitions in a single image. In this thesis, we propose a patch-as-filter method focusing on solving the SD tasks with few-shot learning. Firstly, a patch in an individual image is detected. Then, transformations are learned to create sample-specific convolutional filters. After applying these filters on the original input images, we, lastly, acquire feature maps indicating the duplicate segments. We show experimentally that our approach achieves the state-of-the-art few-shot performance on the Synthetic Visual Reasoning Test (SVRT) SD tasks by accuracy going up above 30% on average, with only ten training samples. Besides that, to further evaluate the effectiveness of our approach, SVRT-like tasks are generated with more difficult visual reasoning concepts. The results suggest that the average accuracy is increased by approximately 10% compared to several popular few-shot algorithms. The method we suggest here has shed new light upon new CNN approaches in solving the SD tasks with few-shot learning."]},{"key":"dc:title","label":"Title","values":["A Patch-as-Filter Method for Same-Different Problems with Few-Shot Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Ling, Charles"],"dc:creator":["Hu, Yining"],"dc:date.accessioned":["2025-07-10T18:36:39Z"],"dc:date.available":["2025-07-10T18:36:39Z"],"dc:date.issued":["2020-04-24"],"dc:description":["The thesis cover page in the PDF document includes references to Western University’s previous institutional repository platform, known as Scholarship@Western, and links to that platform (beginning with ir.lib.uwo.ca). In citing or referring to this thesis, use the DOI or handle from this page instead. Sample citation: Author name, \"Thesis title.\" (Year). Western University Open Repository. https://doi.org/10.71858/123456."],"dc:description.abstract":["Convolutional Neural Network (CNN) has undergone tremendous advancements in recent years, but visual reasoning tasks are still a huge undertaking, particularly in few-shot learning cases. Little is known, especially in solving the Same-Different (SD) task, which is a type of visual reasoning task that requires seeking pattern repetitions in a single image. In this thesis, we propose a patch-as-filter method focusing on solving the SD tasks with few-shot learning. Firstly, a patch in an individual image is detected. Then, transformations are learned to create sample-specific convolutional filters. After applying these filters on the original input images, we, lastly, acquire feature maps indicating the duplicate segments. We show experimentally that our approach achieves the state-of-the-art few-shot performance on the Synthetic Visual Reasoning Test (SVRT) SD tasks by accuracy going up above 30% on average, with only ten training samples. Besides that, to further evaluate the effectiveness of our approach, SVRT-like tasks are generated with more difficult visual reasoning concepts. The results suggest that the average accuracy is increased by approximately 10% compared to several popular few-shot algorithms. The method we suggest here has shed new light upon new CNN approaches in solving the SD tasks with few-shot learning."],"dc:identifier.uri":["https://hdl.handle.net/20.500.14721/30050"],"dc:language.iso":["en_ca"],"dc:publisher":["The University of Western Ontario"],"dc:subject":["Visual reasoning","Few-shot learning","Dynamic filters","Convolutional Neural Network"],"dc:title":["A Patch-as-Filter Method for Same-Different Problems with Few-Shot Learning"],"dc:type":["thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["M Sc"]},"updated_at":"2026-07-27T21:56:14Z"}