DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Kibok | ko |
dc.contributor.author | Lee, Kimin | ko |
dc.contributor.author | Shin, Jinwoo | ko |
dc.contributor.author | Lee, Honglak | ko |
dc.date.accessioned | 2023-08-04T00:00:36Z | - |
dc.date.available | 2023-08-04T00:00:36Z | - |
dc.date.created | 2023-07-07 | - |
dc.date.created | 2023-07-07 | - |
dc.date.issued | 2019-06 | - |
dc.identifier.citation | 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019, pp.29 - 32 | - |
dc.identifier.issn | 2160-7508 | - |
dc.identifier.uri | http://hdl.handle.net/10203/311140 | - |
dc.description.abstract | We propose to leverage a continuous and large stream of unlabeled data in the wild to alleviate catastrophic forgetting in class-incremental learning. Our experimental results on CIFAR and ImageNet datasets demonstrate the superiority of the proposed methods over prior methods: compared to the state-of-the-art method, our proposed method shows up to 14.9% higher accuracy and 45.9% less forgetting. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Incremental learning with unlabeled data in the wild | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85113829002 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 29 | - |
dc.citation.endingpage | 32 | - |
dc.citation.publicationname | 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Long Beach, Ca | - |
dc.contributor.localauthor | Lee, Kimin | - |
dc.contributor.localauthor | Shin, Jinwoo | - |
dc.contributor.nonIdAuthor | Lee, Kibok | - |
dc.contributor.nonIdAuthor | Lee, Honglak | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.