Publications
Detailed Information
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Heo, Byeongho | - |
dc.contributor.author | Lee, Minsik | - |
dc.contributor.author | Yun, Sangdoo | - |
dc.contributor.author | Choi, Jin Young | - |
dc.date.accessioned | 2022-10-26T07:22:46Z | - |
dc.date.available | 2022-10-26T07:22:46Z | - |
dc.date.created | 2022-10-18 | - |
dc.date.issued | 2019-01 | - |
dc.identifier.citation | THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, pp.3771-3778 | - |
dc.identifier.issn | 2159-5399 | - |
dc.identifier.uri | https://hdl.handle.net/10371/186894 | - |
dc.description.abstract | Many recent works on knowledge distillation have provided ways to transfer the knowledge of a trained network for improving the learning process of a new one, but finding a good technique for knowledge distillation is still an open problem. In this paper, we provide a new perspective based on a decision boundary, which is one of the most important component of a classifier. The generalization performance of a classifier is closely related to the adequacy of its decision boundary, so a good classifier bears a good decision boundary. Therefore, transferring information closely related to the decision boundary can be a good attempt for knowledge distillation. To realize this goal, we utilize an adversarial attack to discover samples supporting a decision boundary. Based on this idea, to transfer more accurate information about the decision boundary, the proposed algorithm trains a student classifier based on the adversarial samples supporting the decision boundary. Experiments show that the proposed method indeed improves knowledge distillation and achieves the state-of-the-arts performance. | - |
dc.language | 영어 | - |
dc.publisher | ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE | - |
dc.title | Knowledge Distillation with Adversarial Samples Supporting Decision Boundary | - |
dc.type | Article | - |
dc.identifier.doi | 10.1609/aaai.v33i01.33013771 | - |
dc.citation.journaltitle | THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | - |
dc.identifier.wosid | 000485292603097 | - |
dc.identifier.scopusid | 2-s2.0-85076688758 | - |
dc.citation.endpage | 3778 | - |
dc.citation.startpage | 3771 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Choi, Jin Young | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.