DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Junmo | - |
dc.contributor.advisor | 김준모 | - |
dc.contributor.author | Lee, Chanho | - |
dc.date.accessioned | 2019-09-04T02:41:02Z | - |
dc.date.available | 2019-09-04T02:41:02Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=843367&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/266749 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.2,[iii, 19 p. :] | - |
dc.description.abstract | Although deep neural network has high performance on image classification, it suffers from the lack of ability to distinguish between normal inputs and abnormal inputs, e.g. adversarial examples and out-of-distribution samples. Since deep neural network with softmax classifier is overconfident, detecting out-of-distribution samples only with softmax prediction seems to be insufficient. ODIN is the baseline approach to detect out-of-distribution samples by adding small perturbation which increases the softmax score. This preprocessing technique is widely adopted on state-of-the-art out-of-distribution detection methods. Despite the efficiency of ODIN, its linear approximation restricts theoretical approach and curvature analysis. In this work, we propose additional input preprocessing method named Second Eigenvector Perturbation which observes local curvature by Hessian matrix. Our method improves out-of-distribution detection performance compared with ODIN. Furthermore, we visualize data landscapes to give intuition of the effect of input preprocessing and demonstrate that out-of-distribution with irregular landscape experiences input preprocessing differently. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep learning▼amachine learning▼aneural network▼aout-of-distribution▼aadversarial perturbation▼ahessian matrix | - |
dc.subject | 딥 러닝▼a머신 러닝▼a심층신경망▼a분포 밖 데이터▼a적대적 간섭▼a헤시안 행렬 | - |
dc.title | Improving out-of-distribution image detection via second eigenvector perturbation | - |
dc.title.alternative | 고유벡터 간섭을 통한 분포 밖 데이터 검출 기법 개선 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 이찬호 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.