DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Seungho | ko |
dc.contributor.author | Lee, Minhyun | ko |
dc.contributor.author | Lee, Jongwuk | ko |
dc.contributor.author | Shim, Hyunjung | ko |
dc.date.accessioned | 2022-08-24T07:01:02Z | - |
dc.date.available | 2022-08-24T07:01:02Z | - |
dc.date.created | 2022-07-07 | - |
dc.date.issued | 2021-06 | - |
dc.identifier.citation | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021, pp.5491 - 5501 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10203/298074 | - |
dc.description.abstract | Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects. To overcome these challenges, we propose a novel framework, namely Explicit Pseudo-pixel Supervision (EPS), which learns from pixel-level feedback by combining two weak supervisions; the image-level label provides the object identity via the localization map and the saliency map from the off-the-shelf saliency detection model offers rich boundaries. We devise a joint training strategy to fully utilize the complementary relationship between both information. Our method can obtain accurate object boundaries and discard co-occurring pixels, thereby significantly improving the quality of pseudo-masks. Experimental results show that the proposed method remarkably outperforms existing methods by resolving key challenges of WSSS and achieves the new state-of-the-art performance on both PASCAL VOC 2012 and MS COCO 2014 datasets. The code is available at https://github.com/halbielee/EPS. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85123176803 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 5491 | - |
dc.citation.endingpage | 5501 | - |
dc.citation.publicationname | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.identifier.doi | 10.1109/CVPR46437.2021.00545 | - |
dc.contributor.localauthor | Shim, Hyunjung | - |
dc.contributor.nonIdAuthor | Lee, Seungho | - |
dc.contributor.nonIdAuthor | Lee, Minhyun | - |
dc.contributor.nonIdAuthor | Lee, Jongwuk | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.