Patch-wise contrastive style learning for instagram filter removal

Name: Patch-wise contrastive style learning for instagram filter removal
Author: Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan

İsim	Patch-wise contrastive style learning for instagram filter removal
Yazar	Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan
Basım Tarihi:	2022
Basım Yeri	- IEEE
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-166548739-9
Kayıt Numarası	0cc0d85d-7f88-46a2-9cf2-f69ab0b2bf1a
Lokasyon	Computer Science
Tarih	2022
Örnek Metin	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.
DOI	10.1109/CVPRW56347.2022.00073
Cilt	2022-June

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Patch-wise contrastive style learning for instagram filter removal

Yazar Kınlı, Osman Furkan, Özcan, Barış, Kıraç, Mustafa Furkan

Basım Tarihi 2022

Basım Yeri - IEEE

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-166548739-9

Kayıt Numarası 0cc0d85d-7f88-46a2-9cf2-f69ab0b2bf1a

Lokasyon Computer Science

Tarih 2022

Örnek Metin 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.

DOI 10.1109/CVPRW56347.2022.00073

Cilt 2022-June