DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Wonwoo | ko |
dc.contributor.author | Choo, Jaegul | ko |
dc.date.accessioned | 2023-03-16T08:00:42Z | - |
dc.date.available | 2023-03-16T08:00:42Z | - |
dc.date.created | 2023-03-08 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.citation | 17th European Conference on Computer Vision (ECCV), pp.658 - 674 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10203/305642 | - |
dc.description.abstract | In open-set recognition (OSR), classifiers should be able to reject unknown-class samples while maintaining high closed-set classification accuracy. To effectively solve the OSR problem, previous studies attempted to limit latent feature space and reject data located outside the limited space via offline analyses, e.g., distance-based feature analyses, or complicated network architectures. To conduct OSR via a simple inference process (without offline analyses) in standard classifier architectures, we use distance-based classifiers instead of conventional Softmax classifiers. Afterwards, we design a background-class regularization strategy, which uses background-class data as surrogates of unknown-class ones during training phase. Specifically, we formulate a novel regularization loss suitable for distance-based classifiers, which reserves sufficiently large class-wise latent feature spaces for known classes and forces background-class samples to be located far away from the limited spaces. Through our extensive experiments, we show that the proposed method provides robust OSR results, while maintaining high closed-set classification accuracy. | - |
dc.language | English | - |
dc.publisher | SPRINGER INTERNATIONAL PUBLISHING AG | - |
dc.title | Towards Accurate Open-Set Recognition via Background-Class Regularization | - |
dc.type | Conference | - |
dc.identifier.wosid | 000904201700038 | - |
dc.identifier.scopusid | 2-s2.0-85142683797 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 658 | - |
dc.citation.endingpage | 674 | - |
dc.citation.publicationname | 17th European Conference on Computer Vision (ECCV) | - |
dc.identifier.conferencecountry | IS | - |
dc.identifier.conferencelocation | Tel Aviv | - |
dc.identifier.doi | 10.1007/978-3-031-19806-9_38 | - |
dc.contributor.localauthor | Choo, Jaegul | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.