Robust visual recognition in poor visibility conditions: a prior knowledge-guided adversarial learning approach
Deep learning has achieved remarkable success in numerous computer vision tasks. However, recent research reveals that deep neural networks are vulnerable to natural perturbations from poor visibility conditions, limiting their practical applications. While several studies have focused on enhancing...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171563 |
| _version_ | 1811679297369276416 |
|---|---|
| author | Yang, Jiangang Yang, Jianfei Luo, Luqing Wang, Yun Wang, Shizheng Liu, Jian |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Yang, Jiangang Yang, Jianfei Luo, Luqing Wang, Yun Wang, Shizheng Liu, Jian |
| author_sort | Yang, Jiangang |
| collection | NTU |
| description | Deep learning has achieved remarkable success in numerous computer vision tasks. However, recent research reveals that deep neural networks are vulnerable to natural perturbations from poor visibility conditions, limiting their practical applications. While several studies have focused on enhancing model robustness in poor visibility conditions through techniques such as image restoration, data augmentation, and unsupervised domain adaptation, these efforts are predominantly confined to specific scenarios and fail to address multiple poor visibility scenarios encountered in real-world settings. Furthermore, the valuable prior knowledge inherent in poor visibility images is seldom utilized to aid in resolving high-level computer vision tasks. In light of these challenges, we propose a novel deep learning paradigm designed to bolster the robustness of object recognition across diverse poor visibility scenes. By observing the prior information in diverse poor visibility scenes, we integrate a feature matching module based on this prior knowledge into our proposed learning paradigm, aiming to facilitate deep models in learning more robust generic features at shallow levels. Moreover, to further enhance the robustness of deep features, we employ an adversarial learning strategy based on mutual information. This strategy combines the feature matching module to extract task-specific representations from low visibility scenes in a more robust manner, thereby enhancing the robustness of object recognition. We evaluate our approach on self-constructed datasets containing diverse poor visibility scenes, including visual blur, fog, rain, snow, and low illuminance. Extensive experiments demonstrate that our proposed method yields significant improvements over existing solutions across various poor visibility conditions. |
| first_indexed | 2024-10-01T03:06:55Z |
| format | Journal Article |
| id | ntu-10356/171563 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:06:55Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1715632023-11-03T15:40:23Z Robust visual recognition in poor visibility conditions: a prior knowledge-guided adversarial learning approach Yang, Jiangang Yang, Jianfei Luo, Luqing Wang, Yun Wang, Shizheng Liu, Jian School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Robust Visual Recognition Poor Visibility Conditions Deep learning has achieved remarkable success in numerous computer vision tasks. However, recent research reveals that deep neural networks are vulnerable to natural perturbations from poor visibility conditions, limiting their practical applications. While several studies have focused on enhancing model robustness in poor visibility conditions through techniques such as image restoration, data augmentation, and unsupervised domain adaptation, these efforts are predominantly confined to specific scenarios and fail to address multiple poor visibility scenarios encountered in real-world settings. Furthermore, the valuable prior knowledge inherent in poor visibility images is seldom utilized to aid in resolving high-level computer vision tasks. In light of these challenges, we propose a novel deep learning paradigm designed to bolster the robustness of object recognition across diverse poor visibility scenes. By observing the prior information in diverse poor visibility scenes, we integrate a feature matching module based on this prior knowledge into our proposed learning paradigm, aiming to facilitate deep models in learning more robust generic features at shallow levels. Moreover, to further enhance the robustness of deep features, we employ an adversarial learning strategy based on mutual information. This strategy combines the feature matching module to extract task-specific representations from low visibility scenes in a more robust manner, thereby enhancing the robustness of object recognition. We evaluate our approach on self-constructed datasets containing diverse poor visibility scenes, including visual blur, fog, rain, snow, and low illuminance. Extensive experiments demonstrate that our proposed method yields significant improvements over existing solutions across various poor visibility conditions. Published version This research was funded by SunwayAI computing platform (SXHZ202103) and the National Key Research and Development Program (2021YFB2501403). 2023-10-31T01:35:55Z 2023-10-31T01:35:55Z 2023 Journal Article Yang, J., Yang, J., Luo, L., Wang, Y., Wang, S. & Liu, J. (2023). Robust visual recognition in poor visibility conditions: a prior knowledge-guided adversarial learning approach. Electronics, 12(17), 3711-. https://dx.doi.org/10.3390/electronics12173711 2079-9292 https://hdl.handle.net/10356/171563 10.3390/electronics12173711 2-s2.0-85170540918 17 12 3711 en Electronics © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). application/pdf |
| spellingShingle | Engineering::Electrical and electronic engineering Robust Visual Recognition Poor Visibility Conditions Yang, Jiangang Yang, Jianfei Luo, Luqing Wang, Yun Wang, Shizheng Liu, Jian Robust visual recognition in poor visibility conditions: a prior knowledge-guided adversarial learning approach |
| title | Robust visual recognition in poor visibility conditions: a prior knowledge-guided adversarial learning approach |
| title_full | Robust visual recognition in poor visibility conditions: a prior knowledge-guided adversarial learning approach |
| title_fullStr | Robust visual recognition in poor visibility conditions: a prior knowledge-guided adversarial learning approach |
| title_full_unstemmed | Robust visual recognition in poor visibility conditions: a prior knowledge-guided adversarial learning approach |
| title_short | Robust visual recognition in poor visibility conditions: a prior knowledge-guided adversarial learning approach |
| title_sort | robust visual recognition in poor visibility conditions a prior knowledge guided adversarial learning approach |
| topic | Engineering::Electrical and electronic engineering Robust Visual Recognition Poor Visibility Conditions |
| url | https://hdl.handle.net/10356/171563 |
| work_keys_str_mv | AT yangjiangang robustvisualrecognitioninpoorvisibilityconditionsapriorknowledgeguidedadversariallearningapproach AT yangjianfei robustvisualrecognitioninpoorvisibilityconditionsapriorknowledgeguidedadversariallearningapproach AT luoluqing robustvisualrecognitioninpoorvisibilityconditionsapriorknowledgeguidedadversariallearningapproach AT wangyun robustvisualrecognitioninpoorvisibilityconditionsapriorknowledgeguidedadversariallearningapproach AT wangshizheng robustvisualrecognitioninpoorvisibilityconditionsapriorknowledgeguidedadversariallearningapproach AT liujian robustvisualrecognitioninpoorvisibilityconditionsapriorknowledgeguidedadversariallearningapproach |