Deep saliency with encoded low level distance map and high level features저레벨 차이 맵과 CNN의 고레벨 성분을 이용한 핵심 영역 검출

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 793
  • Download : 0
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.
Advisors
Kim, Junmoresearcher김준모researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2016
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2016.8 ,[iv, 25 p. :]

Keywords

Salient region detection; Convolutional neural network; low level features; high level features; saliency; 핵심 영역 검출; 저레벨 성분 차이; 고레벨 성분; 신경망; 핵심 영역

URI
http://hdl.handle.net/10203/221701
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=663455&flag=dissertation
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0