Twin Adversarial Contrastive Learning for Underwater Image Enhancement and Beyond

By Risheng Liu, Zhiying Jiang, Shuzhou Yang, Xin-Yue Fan. IEEE Transactions on Image Processing, 2022

353 citations recorded by the source corpus.

Underwater images suffer from severe distortion, which degrades the accuracy of object detection performed in an underwater environment. Existing underwater image enhancement algorithms focus on the restoration of contrast and scene reflection. In practice, the enhanced images may not benefit the effectiveness of detection and even lead to a severe performance drop. In this paper, we propose an object-guided twin adversarial contrastive learning based underwater enhancement method to achieve both visual-friendly and task-orientated enhancement. Concretely, we first develop a bilateral constrained closed-loop adversarial enhancement module, which eases the requirement of paired data with the unsupervised manner and preserves more informative features by coupling with the twin inverse mapping. In addition, to confer the restored images with a more realistic appearance, we also adopt the contrastive cues in the training phase. To narrow the gap between visually-oriented and detection-favorable target images, a task-aware feedback module is embedded in the enhancement process, where the coherent gradient information of the detector is incorporated to guide the enhancement towards the detection-pleasing direction. To validate the performance, we allocate a series of prolific detectors into our framework. Extensive experiments demonstrate that the enhanced results of our method show remarkable amelioration in visual quality, the accuracy of different detectors conducted on our enhanced images has been promoted notably. Moreover, we also conduct a study on semantic segmentation to illustrate how object guidance improves high-level tasks. Code and models are available at https://github.com/Jzy2017/TACL

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5d275c9ba062aae6b6bfb7a7ca40a0176db0b550

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Peixian Zhuang
2. Chongyi Li
3. Xipeng Pan
4. Ling Zhou
5. Weidong Zhang
6. Wenyi Zhao
7. Guohou Li
8. Wei Zhong

Citations in the corpus

• Underwater Image Enhancement via Weighted Wavelet Visual Perception Fusion (2024, background): “Liu et al. [58] designed a goal-guided twin GAN that included an edge-holding closed-loop adversarial enhancement module and a task-aware feedback module, but the excessive number of learning strategies increased the complexity of the model.”
• Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation (2023, background): “Recently, few studies[13, 14, 15, 16, 17] have attempted to design multi-task learning-based loss functions by cascading the fusion network and high-level tasks.”