DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hwang, Sehyun | - |
dc.contributor.author | Lee, Sohyun | - |
dc.contributor.author | Kim, Sungyeon | - |
dc.contributor.author | Ok, Jungseul | - |
dc.contributor.author | Kwak, Suha | - |
dc.date.accessioned | 2022-12-12T00:50:12Z | - |
dc.date.available | 2022-12-12T00:50:12Z | - |
dc.date.created | 2022-12-11 | - |
dc.date.issued | 2022-10-23 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/114633 | - |
dc.description.abstract | We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent analysis on a critical issue from label distribution mismatch between source and target in domain adaptation, we devise a method that addresses the issue for the first time in ADA. At its heart lies a novel sampling strategy, which seeks target data that best approximate the entire target distribution as well as being representative, diverse, and uncertain. The sampled target data are then used not only for supervised learning but also for matching label distributions of source and target domains, leading to remarkable performance improvement. On four public benchmarks, our method substantially outperforms existing methods in every adaptation scenario. | - |
dc.language | English | - |
dc.publisher | Springer Science and Business Media Deutschland GmbH | - |
dc.relation.isPartOf | 17th European Conference on Computer Vision, ECCV 2022 | - |
dc.relation.isPartOf | Proceedings of the 17th European Conference on Computer Vision | - |
dc.title | Combating Label Distribution Shift for Active Domain Adaptation | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | 17th European Conference on Computer Vision, ECCV 2022, pp.549 - 566 | - |
dc.identifier.wosid | 000903572500032 | - |
dc.citation.conferenceDate | 2022-10-23 | - |
dc.citation.conferencePlace | IS | - |
dc.citation.endPage | 566 | - |
dc.citation.startPage | 549 | - |
dc.citation.title | 17th European Conference on Computer Vision, ECCV 2022 | - |
dc.contributor.affiliatedAuthor | Ok, Jungseul | - |
dc.contributor.affiliatedAuthor | Kwak, Suha | - |
dc.identifier.scopusid | 2-s2.0-85142668043 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.