DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Gayoung | ko |
dc.contributor.author | Tai, Yu-Wing | ko |
dc.contributor.author | Kim, Junmo | ko |
dc.date.accessioned | 2018-07-24T01:37:25Z | - |
dc.date.available | 2018-07-24T01:37:25Z | - |
dc.date.created | 2017-11-28 | - |
dc.date.created | 2017-11-28 | - |
dc.date.issued | 2018-07 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.40, no.7, pp.1599 - 1610 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10203/243687 | - |
dc.description.abstract | Recent advances in saliency detection have utilized deep learning to obtain high-level features to detect salient regions in scenes. In this paper, we propose ELD-Net, a unified deep learning framework for accurate and efficient saliency detection. We show that hand-crafted features can provide complementary information to enhance saliency detection that uses only high-level features. Our method uses both low-level and high-level features for saliency detection. High-level features are extracted using GoogLeNet, and low-level features evaluate the relative importance of a local region using its differences from other regions in an image. The two feature maps are independently encoded by the convolutional and the ReLU layers. The encoded low-level and high-level features are then combined by concatenation and convolution. Finally, a linear fully connected layer is used to evaluate the saliency of a queried region. A full resolution saliency map is obtained by querying the saliency of each local region of an image. Since the high-level features are encoded at low resolution, and the encoded high-level features can be reused for every query region, our ELD-Net is very fast. Our experiments show that our method outperforms state-of-the-art deep learning-based saliency detection methods. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.subject | REGION DETECTION | - |
dc.subject | NETWORKS | - |
dc.title | ELD-Net: An efficient deep learning architecture for accurate saliency detection | - |
dc.type | Article | - |
dc.identifier.wosid | 000434294800005 | - |
dc.identifier.scopusid | 2-s2.0-85028961360 | - |
dc.type.rims | ART | - |
dc.citation.volume | 40 | - |
dc.citation.issue | 7 | - |
dc.citation.beginningpage | 1599 | - |
dc.citation.endingpage | 1610 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.identifier.doi | 10.1109/TPAMI.2017.2737631 | - |
dc.contributor.localauthor | Tai, Yu-Wing | - |
dc.contributor.localauthor | Kim, Junmo | - |
dc.contributor.nonIdAuthor | Lee, Gayoung | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Salient region detection | - |
dc.subject.keywordAuthor | feature extraction | - |
dc.subject.keywordAuthor | superpixel | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | convolutional neural network (CNN) | - |
dc.subject.keywordPlus | REGION DETECTION | - |
dc.subject.keywordPlus | NETWORKS | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.