Object-stable unsupervised dual contrastive learning image-to-image translation with query-selected attention and convolutional block attention module
Yunseok Oh,
Seonhye Oh,
Sangwoo Noh,
Hangyu Kim and
Hyeon Seo
PLOS ONE, 2023, vol. 18, issue 11, 1-17
Abstract:
Recently, contrastive learning has gained popularity in the field of unsupervised image-to-image (I2I) translation. In a previous study, a query-selected attention (QS-Attn) module, which employed an attention matrix with a probability distribution, was used to maximize the mutual information between the source and translated images. This module selected significant queries using an entropy metric computed from the attention matrix. However, it often selected many queries with equal significance measures, leading to an excessive focus on the background. In this study, we proposed a dual-learning framework with QS-Attn and convolutional block attention module (CBAM) called object-stable dual contrastive learning generative adversarial network (OS-DCLGAN). In this paper, we utilize a CBAM, which learns what and where to emphasize or suppress, thereby refining intermediate features effectively. This CBAM was integrated before the QS-Attn module to capture significant domain information for I2I translation tasks. The proposed framework outperformed recently introduced approaches in various I2I translation tasks, showing its effectiveness and versatility. The code is available at https://github.com/RedPotatoChip/OSUDL
Date: 2023
References: View complete reference list from CitEc
Citations:
Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0293885 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 93885&type=printable (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0293885
DOI: 10.1371/journal.pone.0293885
Access Statistics for this article
More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().