DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Junmo | - |
dc.contributor.advisor | 김준모 | - |
dc.contributor.author | Gayoung, Lee | - |
dc.contributor.author | 이가영 | - |
dc.date.accessioned | 2017-03-29T02:37:23Z | - |
dc.date.available | 2017-03-29T02:37:23Z | - |
dc.date.issued | 2016 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=663455&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/221701 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2016.8 ,[iv, 25 p. :] | - |
dc.description.abstract | Recent advances in saliency detection have utilized deep learning to obtain high level features to detect salient regions in a scene. These advances have demonstrated superior results over previous works that utilize hand-crafted low level features for saliency detection. In this paper, we demonstrate that hand-crafted features can provide complementary information to enhance performance of saliency detection that utilizes only high level features. Our method utilizes both high level and low level features for saliency detection under a unified deep learning framework. The high level features are extracted using the VGG-net, and the low level features are compared with other parts of an image to form a low level distance map. The low level distance map is then encoded using a convolutional neural network(CNN) with multiple $1 \times 1$ convolutional and ReLU layers. We concatenate the encoded low level distance map and the high level features, and connect them to a fully connected neural network classifier to evaluate the saliency of a query region. Our experiments show that our method can further improve the performance of state-of-the-art deep learning-based saliency detection methods. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Salient region detection | - |
dc.subject | Convolutional neural network | - |
dc.subject | low level features | - |
dc.subject | high level features | - |
dc.subject | saliency | - |
dc.subject | 핵심 영역 검출 | - |
dc.subject | 저레벨 성분 차이 | - |
dc.subject | 고레벨 성분 | - |
dc.subject | 신경망 | - |
dc.subject | 핵심 영역 | - |
dc.title | Deep saliency with encoded low level distance map and high level features | - |
dc.title.alternative | 저레벨 차이 맵과 CNN의 고레벨 성분을 이용한 핵심 영역 검출 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.