DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jo, Sanghyun | ko |
dc.contributor.author | Yu, In Jae | ko |
dc.date.accessioned | 2023-09-06T08:00:34Z | - |
dc.date.available | 2023-09-06T08:00:34Z | - |
dc.date.created | 2023-09-06 | - |
dc.date.issued | 2021-09-19 | - |
dc.identifier.citation | 2021 IEEE International Conference on Image Processing (ICIP), pp.639 - 643 | - |
dc.identifier.issn | 1522-4880 | - |
dc.identifier.uri | http://hdl.handle.net/10203/312265 | - |
dc.description.abstract | Weakly-supervised semantic segmentation (WSSS) is introduced to narrow the gap for semantic segmentation performance from pixel-level supervision to image-level supervision. Most advanced approaches are based on class activation maps (CAMs) to generate pseudo-labels to train the segmentation network. The main limitation of WSSS is that the process of generating pseudo-labels from CAMs that use an image classifier is mainly focused on the most discriminative parts of the objects. To address this issue, we propose Puzzle-CAM, a process that minimizes differences between the features from separate patches and the whole image. Our method consists of a puzzle module and two regularization terms to discover the most integrated region in an object. Puzzle-CAM can activate the overall region of an object using image-level supervision without requiring extra parameters. In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 dataset. Code associated with our experiments is available at https://github.com/OFRIN/PuzzleCAM. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Puzzle-CAM: Improved Localization Via Matching Partial And Full Features | - |
dc.type | Conference | - |
dc.identifier.wosid | 000819455100128 | - |
dc.identifier.scopusid | 2-s2.0-85125581227 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 639 | - |
dc.citation.endingpage | 643 | - |
dc.citation.publicationname | 2021 IEEE International Conference on Image Processing (ICIP) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Anchorage, AK | - |
dc.identifier.doi | 10.1109/icip42928.2021.9506058 | - |
dc.contributor.nonIdAuthor | Jo, Sanghyun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.