Please use this identifier to cite or link to this item:
Title: Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond
Authors: Yu, Yi
Yang, Wenhan
Tan, Yap Peng
Kot, Alex Chichung
Keywords: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Issue Date: 2022
Source: Yu, Y., Yang, W., Tan, Y. P. & Kot, A. C. (2022). Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond. 2022 IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 6013-6022.
metadata.dc.contributor.conference: 2022 IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR)
Abstract: Rain removal aims to remove rain streaks from images/videos and reduce the disruptive effects caused by rain. It not only enhances image/video visibility but also allows many computer vision algorithms to function properly. This paper makes the first attempt to conduct a comprehensive study on the robustness of deep learning-based rain removal methods against adversarial attacks. Our study shows that, when the image/video is highly degraded, rain removal methods are more vulnerable to the adversarial attacks as small distortions/perturbations become less noticeable or detectable. In this paper, we first present a comprehensive empirical evaluation of various methods at different levels of attacks and with various losses/targets to generate the perturbations from the perspective of human perception and machine analysis tasks. A systematic evaluation of key modules in existing methods is performed in terms of their robustness against adversarial attacks. From the insights of our analysis, we construct a more robust deraining method by integrating these effective modules. Finally, we examine various types of adversarial attacks that are specific to deraining problems and their effects on both human and machine vision tasks, including 1) rain region attacks, adding perturbations only in the rain regions to make the perturbations in the attacked rain images less visible; 2) object-sensitive attacks, adding perturbations only in regions near the given objects. Code is available at
Schools: Interdisciplinary Graduate School (IGS) 
School of Electrical and Electronic Engineering 
Research Centres: Rapid-Rich Object Search (ROSE) Lab 
Rights: © 2022 The Author(s). This CVPR paper is the Open Acess version, provided by the Computer Vision Foundation.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Conference Papers
IGS Conference Papers

Page view(s)

Updated on Sep 21, 2023

Download(s) 50

Updated on Sep 21, 2023

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.