Deep Underwater Image Quality Assessment With Explicit Degradation Awareness Embedding
Jiang, Qiuping Gu, Yuese Wu, Zongwei Li, Chongyi Xiong, Huan Shao, Feng Wang, Zhihua
Jiang, Qiuping
Gu, Yuese
Wu, Zongwei
Li, Chongyi
Xiong, Huan
Shao, Feng
Wang, Zhihua
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Underwater Image Quality Assessment (UIQA) is currently an area of intensive research interest. Existing deep learning-based UIQA models always learn a deep neural network to directly map the input degraded underwater image into a final quality score via end-to-end training. However, a wide variety of image contents or distortion types may correspond to the same quality score, making it challenging to train such a deep model merely with a single subjective quality score as supervision. An intuitive idea to solve this problem is to exploit more detailed degradation-aware information as supplementary guidance to facilitate model learning. In this paper, we devise a novel deep UIQA model with Explicit Degradation Awareness embedding, i.e., EDANet. To train the EDANet, a two-stage training strategy is adopted. First, a tailored Degradation Information Discovery subnetwork (DIDNet) is pre-trained to infer a residual map between the input degraded underwater image and its pseudoreference counterpart. The inferred residual map explicitly characterizes the local degradation of the input underwater image. The intermediate feature representations on the decoder side of DIDNet are then embedded into the Degradation-guided Quality Evaluation subnetwork (DQENet), which significantly enhances the feature characterization capability with higher degradation awareness for quality prediction. The superiority of our EDANet against 18 state-of-the-art methods has been well demonstrated by extensive comparisons on two benchmark datasets. The source code of our EDANet is available at https://github.com/yia-yuese/EDANet.
Citation
C. Jiang, S. Wang, Y. Long, Z. Li, H. Zhang and L. Shao, "Imaginary-Connected Embedding in Complex Space for Unseen Attribute-Object Discrimination," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 3, pp. 1395-1413, March 2025, doi: 10.1109/TPAMI.2024.3487631
Source
IEEE Transactions on Image Processing
Conference
Keywords
Image quality assessment, Underwater image, Degradation awareness, Deep learning
Subjects
Source
Publisher
IEEE