DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Junmo | - |
dc.contributor.advisor | 김준모 | - |
dc.contributor.author | Ahn, Jaesung | - |
dc.date.accessioned | 2021-05-11T19:33:26Z | - |
dc.date.available | 2021-05-11T19:33:26Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=875339&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/283045 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.8,[iii, 22 p. :] | - |
dc.description.abstract | Anomaly detection is a task that distinguishes whether incoming data is normal or abnormal. To give a network the ability to detect anomaly samples, we propose a method that deliberately limiting and distorting information of the data and then restoring original data from such corrupted data by using denoising and inpainting. As most of anomaly detection algorithm does, the reconstruction error would be the measure of abnormality. The main idea behind our proposed method is that the restored data distribution inevitably follows the normal sample distribution if only limited information of the data is provided. Experimental results show that the proposed method is superior to the existing generative model-based abnormal detection method in both quantitative and qualitative aspects. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep learning▼aanomaly detection▼agenerative model | - |
dc.subject | 딥러닝▼a이상치 검출▼a생성 모델 | - |
dc.title | Anomaly detection via end-to-end learning of mask generator and denoising autoencoder | - |
dc.title.alternative | 마스크 생성기와 잡음 제거 오토인코더의 종단간 학습을 통한 이상치 검출 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 안재성 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.