DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Byungju | ko |
dc.contributor.author | Hong, Hyeong Gwon | ko |
dc.contributor.author | Kim, Junmo | ko |
dc.date.accessioned | 2021-10-27T00:50:14Z | - |
dc.date.available | 2021-10-27T00:50:14Z | - |
dc.date.created | 2021-10-27 | - |
dc.date.created | 2021-10-27 | - |
dc.date.issued | 2021-01 | - |
dc.identifier.citation | IEEE Winter Conference on Applications of Computer Vision (WACV), pp.1478 - 1486 | - |
dc.identifier.issn | 2472-6737 | - |
dc.identifier.uri | http://hdl.handle.net/10203/288323 | - |
dc.description.abstract | The imbalanced distribution of the training data makes the networks biased to the frequent classes. Existing methods to resolve the problem involve re-sampling, reweighting, or cost-sensitive learning. Most of them anticipate that emphasizing the minority classes during the training would help the network to learn better representations. In this paper, we propose a method for reparameterizing softmax classifiers' offsets so that training is less sensitive to class imbalance. We first observe that the trained offset of the baseline linear classifier is biased toward the majority classes due to the imbalance. Instead of the trained offset, we define the estimated offset, and constrain it to be uniform over the classes. In experiments with long-tailed benchmarks, our method exhibits the best performance. These experiments verify that our proposed method effectively encourages the networks to learn better representations for minority classes while preserving the performance for the majority classes. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | De-biasing Neural Networks with Estimated Offset for Class Imbalanced Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000692171000147 | - |
dc.identifier.scopusid | 2-s2.0-85116132693 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1478 | - |
dc.citation.endingpage | 1486 | - |
dc.citation.publicationname | IEEE Winter Conference on Applications of Computer Vision (WACV) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | ELECTR NETWORK | - |
dc.identifier.doi | 10.1109/WACV48630.2021.00152 | - |
dc.contributor.localauthor | Kim, Junmo | - |
dc.contributor.nonIdAuthor | Kim, Byungju | - |
dc.contributor.nonIdAuthor | Hong, Hyeong Gwon | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.