Yuhang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuhang Li has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Bolin Gao
Tsinghua University
1 shared publication - Xiangmo Zhao
Chang’an University
1 shared publication - Yang Wang
University of Science and Technology of China
1 shared publication - Yisheng An
School of Information Engineering, Changan University, Xian, Shaanxi, China
1 shared publication - Zhanwen Liu
The School of Information Engineering, Chang'an University, Xi'an, 710000, Shaanxi Province, China
1 shared publication
Latest Publications
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (11) , 7208-7221
Boosting Visual Recognition in Real-World Degradations via Unsupervised Feature Enhancement Module With Deep Channel Prior
The environmental perception of autonomous vehicles in normal conditions have achieved considerable success in the past decade. However, various unfavourable conditions such as fog, low-light, and motion blur will degrade image quality and pose tremendous threats to the safety of autonomous driving. That is, when applied to degraded images, state-of-the-art visual models often suffer performance decline due to the feature content loss and artifact interference caused by statistical and structural properties disruption of captured images. To address this problem, this work proposes a novel Deep Channel Prior (DCP) for degraded visual recognition. Specifically, we observe that, in the deep representation space of pre-trained models, the channel correlations of degraded features with the same degradation type have uniform distribution even if they have different content and semantics, which can facilitate the mapping relationship learning between degraded and clear representations in high-sparsity feature space. Based on this, a novel plug-and-play Unsupervised Feature Enhancement Module (UFEM) is proposed to achieve unsupervised feature correction, where the multi-adversarial mechanism is introduced in the first stage of UFEM to achieve the latent content restoration and artifact removal in high-sparsity feature space. Then, the generated features are transferred to the second stage for global correlation modulation under the guidance of DCP to obtain high-quality and recognition-friendly features. Evaluations of three tasks and eight benchmark datasets demonstrate that our proposed method can comprehensively improve the performance of pre-trained models in real degradation conditions. The source code is available at https://github.com/liyuhang166/Deep_Channel_Prior
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Vehicles
- Vol. 9 (11) , 7208-7221
Boosting Visual Recognition in Real-World Degradations via Unsupervised Feature Enhancement Module With Deep Channel Prior
The environmental perception of autonomous vehicles in normal conditions have achieved considerable success in the past decade. However, various unfavourable conditions such as fog, low-light, and motion blur will degrade image quality and pose tremendous threats to the safety of autonomous driving. That is, when applied to degraded images, state-of-the-art visual models often suffer performance decline due to the feature content loss and artifact interference caused by statistical and structural properties disruption of captured images. To address this problem, this work proposes a novel Deep Channel Prior (DCP) for degraded visual recognition. Specifically, we observe that, in the deep representation space of pre-trained models, the channel correlations of degraded features with the same degradation type have uniform distribution even if they have different content and semantics, which can facilitate the mapping relationship learning between degraded and clear representations in high-sparsity feature space. Based on this, a novel plug-and-play Unsupervised Feature Enhancement Module (UFEM) is proposed to achieve unsupervised feature correction, where the multi-adversarial mechanism is introduced in the first stage of UFEM to achieve the latent content restoration and artifact removal in high-sparsity feature space. Then, the generated features are transferred to the second stage for global correlation modulation under the guidance of DCP to obtain high-quality and recognition-friendly features. Evaluations of three tasks and eight benchmark datasets demonstrate that our proposed method can comprehensively improve the performance of pre-trained models in real degradation conditions. The source code is available at https://github.com/liyuhang166/Deep_Channel_Prior