DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jaehyung, Kim | ko |
dc.contributor.author | Jeong, Jongheon | ko |
dc.contributor.author | Shin, Jinwoo | ko |
dc.date.accessioned | 2020-12-11T02:10:26Z | - |
dc.date.available | 2020-12-11T02:10:26Z | - |
dc.date.created | 2020-12-02 | - |
dc.date.created | 2020-12-02 | - |
dc.date.issued | 2020-06-16 | - |
dc.identifier.citation | IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10203/278207 | - |
dc.description.abstract | In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue by augmenting less-frequent classes via translating samples (e.g., images) from more-frequent classes. This simple approach enables a classifier to learn more generalizable features of minority classes, by transferring and leveraging the diversity of the majority information. Our experimental results on a variety of class-imbalanced datasets show that the proposed method improves the generalization on minority classes significantly compared to other existing re-sampling or re-weighting methods. The performance of our method even surpasses those of previous state-of-the-art methods for the imbalanced classification. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.title | M2m: Imbalanced Classification via Major-to-minor Translation | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85095708632 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.identifier.doi | 10.1109/CVPR42600.2020.01391 | - |
dc.contributor.localauthor | Shin, Jinwoo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.