Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond
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...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/158475 https://openaccess.thecvf.com/menu |
| _version_ | 1826125874273976320 |
|---|---|
| author | Yu, Yi Yang, Wenhan Tan, Yap Peng Kot, Alex Chichung |
| author2 | Interdisciplinary Graduate School (IGS) |
| author_facet | Interdisciplinary Graduate School (IGS) Yu, Yi Yang, Wenhan Tan, Yap Peng Kot, Alex Chichung |
| author_sort | Yu, Yi |
| collection | NTU |
| description | 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 https://github.com/yuyi-sd/Robust_Rain_Removal. |
| first_indexed | 2024-10-01T06:43:51Z |
| format | Conference Paper |
| id | ntu-10356/158475 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:43:51Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1584752022-09-08T06:39:18Z Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond Yu, Yi Yang, Wenhan Tan, Yap Peng Kot, Alex Chichung Interdisciplinary Graduate School (IGS) School of Electrical and Electronic Engineering 2022 IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) Rapid-Rich Object Search (ROSE) Lab Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Computer science and engineering::Computing methodologies::Pattern recognition Rain Sreak Removal Adversarial Attacks 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 https://github.com/yuyi-sd/Robust_Rain_Removal. Nanyang Technological University Submitted/Accepted version This work was done at Rapid-Rich Object Search (ROSE) Lab, Nanyang Technological University. This research is supported in part by the NTUPKU Joint Research Institute (a collaboration between the Nanyang Technological University and Peking University that is sponsored by a donation from the Ng Teng Fong Charitable Foundation). 2022-09-08T06:37:16Z 2022-09-08T06:37:16Z 2022 Conference Paper 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. https://hdl.handle.net/10356/158475 https://openaccess.thecvf.com/menu 6013 6022 en © 2022 The Author(s). This CVPR paper is the Open Acess version, provided by the Computer Vision Foundation. application/pdf |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Computer science and engineering::Computing methodologies::Pattern recognition Rain Sreak Removal Adversarial Attacks Yu, Yi Yang, Wenhan Tan, Yap Peng Kot, Alex Chichung Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond |
| title | Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond |
| title_full | Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond |
| title_fullStr | Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond |
| title_full_unstemmed | Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond |
| title_short | Towards robust rain removal against adversarial attacks: a comprehensive benchmark analysis and beyond |
| title_sort | towards robust rain removal against adversarial attacks a comprehensive benchmark analysis and beyond |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Engineering::Computer science and engineering::Computing methodologies::Pattern recognition Rain Sreak Removal Adversarial Attacks |
| url | https://hdl.handle.net/10356/158475 https://openaccess.thecvf.com/menu |
| work_keys_str_mv | AT yuyi towardsrobustrainremovalagainstadversarialattacksacomprehensivebenchmarkanalysisandbeyond AT yangwenhan towardsrobustrainremovalagainstadversarialattacksacomprehensivebenchmarkanalysisandbeyond AT tanyappeng towardsrobustrainremovalagainstadversarialattacksacomprehensivebenchmarkanalysisandbeyond AT kotalexchichung towardsrobustrainremovalagainstadversarialattacksacomprehensivebenchmarkanalysisandbeyond |