DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Sungnyun | ko |
dc.contributor.author | Bae, Sangmin | ko |
dc.contributor.author | Yun, Seyoung | ko |
dc.date.accessioned | 2023-12-08T02:02:51Z | - |
dc.date.available | 2023-12-08T02:02:51Z | - |
dc.date.created | 2023-12-07 | - |
dc.date.issued | 2023-06-20 | - |
dc.identifier.citation | The IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, pp.7537 - 7547 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10203/316052 | - |
dc.description.abstract | Deep learning in general domains has constantly been extended to domain-specific tasks requiring the recognition of fine-grained characteristics. However, real-world applications for fine-grained tasks suffer from two challenges: a high reliance on expert knowledge for annotation and necessity of a versatile model for various downstream tasks in a specific domain (e.g., prediction of categories, bounding boxes, or pixel-wise annotations). Fortunately, the recent self-supervised learning (SSL) is a promising approach to pretrain a model without annotations, serving as an effective initialization for any downstream tasks. Since SSL does not rely on the presence of annotation, in general, it utilizes the large-scale unlabeled dataset, referred to as an open-set. In this sense, we introduce a novel Open-Set Self-Supervised Learning problem under the assumption that a large-scale unlabeled open-set is available, as well as the fine-grained target dataset, during a pretraining phase. In our problem setup, it is crucial to consider the distribution mismatch between the open-set and target dataset. Hence, we propose SimCore algorithm to sample a coreset, the subset of an open-set that has a minimum distance to the target dataset in the latent space. We demonstrate that SimCore significantly improves representation learning performance through extensive experimental settings, including eleven fine-grained datasets and seven open-sets in various downstream tasks. | - |
dc.language | English | - |
dc.publisher | IEEE/CVF | - |
dc.title | Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 001058542607086 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 7537 | - |
dc.citation.endingpage | 7547 | - |
dc.citation.publicationname | The IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 | - |
dc.identifier.conferencecountry | CN | - |
dc.identifier.conferencelocation | Vancouver | - |
dc.identifier.doi | 10.1109/CVPR52729.2023.00728 | - |
dc.contributor.localauthor | Yun, Seyoung | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.