Publications
Detailed Information
MUTE: Inter-class Ambiguity Driven Multi-hot Target Encoding for Deep Neural Network Design
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jaiswal, Mayoore S. | - |
dc.contributor.author | Kang, Bumsoo | - |
dc.contributor.author | Lee, Jinho | - |
dc.contributor.author | Cho, Minsik | - |
dc.date.accessioned | 2024-05-02T05:59:42Z | - |
dc.date.available | 2024-05-02T05:59:42Z | - |
dc.date.created | 2024-04-23 | - |
dc.date.created | 2024-04-23 | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), pp.3254-3263 | - |
dc.identifier.issn | 2160-7508 | - |
dc.identifier.uri | https://hdl.handle.net/10371/200509 | - |
dc.description.abstract | Target encoding is an effective technique to boost performance of classical and deep neural networks based classification models. However, the existing target encoding approaches require significant increase in the learning capacity, thus demand higher computation power and more training data. In this paper, we present a novel and efficient target encoding method, Inter-class Ambiguity Driven Multi-hot Target Encoding (MUTE), to improve both generalizability and robustness of a classification model by understanding the inter-class characteristics of a target dataset. By evaluating ambiguity between the target classes in a dataset, MUTE strategically optimizes the Hamming distances among target encoding. Such optimized target encoding offers higher classification strength for neural network models with negligible computation overhead and without increasing the model size. When MUTE is applied to the popular image classification networks and datasets, our experimental results show that MUTE offers better generalization and defense against the noises and adversarial attacks over the existing solutions. | - |
dc.language | 영어 | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | MUTE: Inter-class Ambiguity Driven Multi-hot Target Encoding for Deep Neural Network Design | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/CVPRW50498.2020.00385 | - |
dc.citation.journaltitle | 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020) | - |
dc.identifier.wosid | 000788279003038 | - |
dc.identifier.scopusid | 2-s2.0-85090134181 | - |
dc.citation.endpage | 3263 | - |
dc.citation.startpage | 3254 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Lee, Jinho | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Related Researcher
- College of Engineering
- Department of Electrical and Computer Engineering
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.