DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kweon, In So | - |
dc.contributor.advisor | 권인소 | - |
dc.contributor.author | Yoo, Donggeun | - |
dc.date.accessioned | 2019-08-25T02:43:56Z | - |
dc.date.available | 2019-08-25T02:43:56Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=842218&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/265132 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 전기및전자공학부, 2019.2,[viii, 99 p. :] | - |
dc.description.abstract | Traditional obstacles that make the visual recognition problem difficult are the occlusion, within-class diversity, inter-class similarity, geometric/photometric transformations, and background clutters. This dissertation focuses on the background clutters. The recent evolution of deep learning has significantly suppressed the negative effect of backgrounds by learning common visual features of objects from big data that cover diverse backgrounds. However, a deep learning based recognizer still lacks an explicit design to solve this problem but recognizes objects by detecting foreground features common to objects. Therefore, the ability to cope with the background is limited to the background distribution of the training data. In this dissertation, we define problems of background clutters in various visual recognition tasks and presents solutions based on deep learning. The background can be an obstacle to visual recognition, but it can also be an important clue to determine the object existence. We simultaneously take these two aspects of backgrounds into consideration to improve the performance of object classification and detection. Once a target object is classified or detected, the background always acts as an obstacle for another recognizer to analyze attributes of the object. To solve this problem, we learn a normalized object appearance invariant to the backgrounds. When we apply these recognizers to the real world, they often fail to recognize objects with new backgrounds out of the training background distribution. To maintain the recognition performance, we propose an active background adaptation method that enables a recognizer to adapt quickly to the new backgrounds. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep learning▼avisual recognition▼abackground clutters▼aimage classification▼aobject detection▼adomain transfer▼aactive learning | - |
dc.subject | 딥러닝▼a시각 인식▼a배경 교란▼a이미지 분류▼a물체 검출▼a전이 학습▼a능동적 학습 | - |
dc.title | Deep learning based visual recognition robust against background clutters | - |
dc.title.alternative | 배경 교란에 강인한 딥러닝 기반 시각 인식 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 유동근 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.