DC Field | Value | Language |
---|---|---|
dc.contributor.author | Oh, Youngtaek | ko |
dc.contributor.author | Kim, Dong-Jin | ko |
dc.contributor.author | Kweon, In So | ko |
dc.date.accessioned | 2022-11-29T03:01:12Z | - |
dc.date.available | 2022-11-29T03:01:12Z | - |
dc.date.created | 2022-11-25 | - |
dc.date.created | 2022-11-25 | - |
dc.date.issued | 2022-06-24 | - |
dc.identifier.citation | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, pp.9776 - 9786 | - |
dc.identifier.uri | http://hdl.handle.net/10203/301208 | - |
dc.description.abstract | The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms of bias. We further introduce a novel semantic alignment loss to establish balanced feature representation to reduce the biased predictions from the classifier. We term the whole framework as Distribution-Aware Semantics-Oriented (DASO) Pseudo-label. We conduct extensive experiments in a wide range of imbalanced benchmarks: CIFAR10/100-LT, STL10-LT, and large-scale long-tailed Semi-Aves with open-set class, and demonstrate that, the proposed DASO framework reliably improves SSL learners with unlabeled data especially when both (1) class imbalance and (2) distribution mismatch dominate. | - |
dc.language | English | - |
dc.publisher | Computer Vision Foundation, IEEE Computer Society | - |
dc.title | DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000870759102083 | - |
dc.identifier.scopusid | 2-s2.0-85136128659 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 9776 | - |
dc.citation.endingpage | 9786 | - |
dc.citation.publicationname | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | New Orleans | - |
dc.identifier.doi | 10.1109/CVPR52688.2022.00956 | - |
dc.contributor.localauthor | Kweon, In So | - |
dc.contributor.nonIdAuthor | Kim, Dong-Jin | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.