Patch-wise contrastive style learning for instagram filter removal
dc.contributor.author | Kınlı, Osman Furkan | |
dc.contributor.author | Özcan, Barış | |
dc.contributor.author | Kıraç, Mustafa Furkan | |
dc.date.accessioned | 2023-08-12T21:25:52Z | |
dc.date.available | 2023-08-12T21:25:52Z | |
dc.date.issued | 2022 | |
dc.identifier.isbn | 978-166548739-9 | |
dc.identifier.issn | 2160-7508 | en_US |
dc.identifier.uri | http://hdl.handle.net/10679/8647 | |
dc.identifier.uri | https://ieeexplore.ieee.org/document/9857480 | |
dc.description.abstract | Image-level corruptions and perturbations degrade the performance of CNNs on different downstream vision tasks. Social media filters are one of the most common resources of various corruptions and perturbations for real-world visual analysis applications. The negative effects of these dis-tractive factors can be alleviated by recovering the original images with their pure style for the inference of the downstream vision tasks. Assuming these filters substantially inject a piece of additional style information to the social media images, we can formulate the problem of recovering the original versions as a reverse style transfer problem. We introduce Contrastive Instagram Filter Removal Network (CIFR), which enhances this idea for Instagram filter removal by employing a novel multi-layer patch-wise contrastive style learning mechanism. Experiments show our proposed strategy produces better qualitative and quantitative results than the previous studies. Moreover, we present the results of our additional experiments for proposed architecture within different settings. Finally, we present the inference outputs and quantitative comparison of filtered and recovered images on localization and segmentation tasks to encourage the main motivation for this problem. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | IEEE | en_US |
dc.relation.ispartof | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) | |
dc.rights | restrictedAccess | |
dc.title | Patch-wise contrastive style learning for instagram filter removal | en_US |
dc.type | Conference paper | en_US |
dc.publicationstatus | Published | en_US |
dc.contributor.department | Özyeğin University | |
dc.contributor.authorID | (ORCID 0000-0002-9192-6583 & YÖK ID 283852) Kınlı, Furkan | |
dc.contributor.authorID | (ORCID 0000-0001-9177-0489 & YÖK ID 124619) Kıraç, Furkan | |
dc.contributor.ozuauthor | Kınlı, Osman Furkan | |
dc.contributor.ozuauthor | Kıraç, Mustafa Furkan | |
dc.identifier.volume | 2022-June | en_US |
dc.identifier.startpage | 577 | en_US |
dc.identifier.endpage | 587 | en_US |
dc.identifier.wos | WOS:000861612700064 | |
dc.identifier.doi | 10.1109/CVPRW56347.2022.00073 | en_US |
dc.identifier.scopus | SCOPUS:2-s2.0-85137206316 | |
dc.contributor.ozugradstudent | Özcan, Barış | |
dc.relation.publicationcategory | Conference Paper - International - Institutional Academic Staff and PhD Student |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
Share this page