Mitigating Search Interference with Task-Aware Nested Search
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Jiho | - |
dc.contributor.author | Kim, Eunwoo | - |
dc.date.accessioned | 2024-05-20T08:30:16Z | - |
dc.date.available | 2024-05-20T08:30:16Z | - |
dc.date.issued | 2024 | - |
dc.identifier.issn | 1057-7149 | - |
dc.identifier.issn | 1941-0042 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/73794 | - |
dc.description.abstract | Neural Architecture Search (NAS) has emerged as a promising tool in the field of AutoML for designing more accurate and efficient architectures. The majority of NAS works employ a weight-sharing technique to reduce the search cost by sharing the weights of a supernet, which is a composite of all architectures produced from the search space. Nonetheless, this method has a significant drawback in that negative interference may arise when candidate architectures share the same weights. This issue becomes even more severe in multi-task searches, where a supernet is shared across tasks. To address this problem, we propose a task-aware nested search for multiple tasks that generates task-specific search spaces and architectures using a search-in-search approach consisting of space-search and architecture-search phases. In the space-search phase, we discover an optimal subspace in a task-aware manner by utilizing the proposed search space generator based on the global search space. On top of each subspace, we search for a promising architecture in the architecture-search phase. This method can mitigate search interference by adaptively sharing weights of the supernet by the generated subspace. The experimental results on various vision benchmarks (CityScapes, NYUv2, and Tiny-Taskonomy) show that the proposed method achieves outstanding performance over existing methods in terms of task accuracy, model parameters, and latency. IEEE | - |
dc.format.extent | 13 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Mitigating Search Interference with Task-Aware Nested Search | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/TIP.2024.3390996 | - |
dc.identifier.bibliographicCitation | IEEE Transactions on Image Processing, v.33, pp 3102 - 3114 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.wosid | 001214554700009 | - |
dc.identifier.scopusid | 2-s2.0-85191342488 | - |
dc.citation.endPage | 3114 | - |
dc.citation.startPage | 3102 | - |
dc.citation.title | IEEE Transactions on Image Processing | - |
dc.citation.volume | 33 | - |
dc.type.docType | Article | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordAuthor | multi-task learning | - |
dc.subject.keywordAuthor | Neural architecture search | - |
dc.subject.keywordAuthor | search interference | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.