DC Field | Value | Language |
---|---|---|
dc.contributor.author | Bae, Woong | ko |
dc.contributor.author | Yoo, Jaejun | ko |
dc.contributor.author | Ye, Jong Chul | ko |
dc.date.accessioned | 2018-02-21T04:22:26Z | - |
dc.date.available | 2018-02-21T04:22:26Z | - |
dc.date.created | 2017-12-05 | - |
dc.date.created | 2017-12-05 | - |
dc.date.created | 2017-12-05 | - |
dc.date.issued | 2017-07 | - |
dc.identifier.citation | 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp.1141 - 1149 | - |
dc.identifier.issn | 2160-7508 | - |
dc.identifier.uri | http://hdl.handle.net/10203/239693 | - |
dc.description.abstract | The latest deep learning approaches perform better than the state-of-the-art signal processing approaches in various image restoration tasks. However, if an image contains many patterns and structures, the performance of these CNNs is still inferior. To address this issue, here we propose a novel feature space deep residual learning algorithm that outperforms the existing residual learning. The main idea is originated from the observation that the performance of a learning algorithm can be improved if the input and/or label manifolds can be made topologically simpler by an analytic mapping to a feature space. Our extensive numerical studies using denoising experiments and NTIRE single-image super-resolution (SISR) competition demonstrate that the proposed feature space residual learning outperforms the existing state-of-the-art approaches. Moreover, our algorithm was ranked third in NTIRE competition with 5-10 times faster computational time compared to the top ranked teams. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society and the Computer Vision Foundation (CVF) | - |
dc.title | Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification | - |
dc.type | Conference | - |
dc.identifier.wosid | 000426448300145 | - |
dc.identifier.scopusid | 2-s2.0-85030260146 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1141 | - |
dc.citation.endingpage | 1149 | - |
dc.citation.publicationname | 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Hawaii Convention Center | - |
dc.identifier.doi | 10.1109/CVPRW.2017.152 | - |
dc.contributor.localauthor | Ye, Jong Chul | - |
dc.contributor.nonIdAuthor | Bae, Woong | - |
dc.contributor.nonIdAuthor | Yoo, Jaejun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.