Real-World Image Super-Resolution as Multi-Task Learning

In this paper, we take a new look at real-world image super-resolution (real-SR) from a multi-task learning perspective. We demonstrate that the conventional formulation of real-SR can be viewed as solving multiple distinct degradation tasks using a single shared model. This poses a challenge known as task competition or task conflict in multi-task learning, where certain tasks dominate the learning process, resulting in poor performance on other tasks. This problem is exacerbated in the case of real-SR, due to the involvement of numerous degradation tasks. To address the issue of task competition in real-SR, we propose a task grouping approach. Our approach efficiently identifies the degradation tasks where a real-SR model falls short and groups these unsatisfactory tasks into multiple task groups. We then utilize the task groups to fine-tune the real-SR model in a simple way, which effectively mitigates task competition and facilitates knowledge transfer. Extensive experiments demonstrate our method achieves significantly enhanced performance across a wide range of degradation scenarios.

Authors

• Wenlong Zhang Arizona State University
• Xiaohui Li
• Guangyuan SHI
• Xiangyu Chen Institute of Artificial Intelligence (TeleAI), China Telecom
• Yu Qiao Shanghai Artificial Intelligence Laboratory
• Xiaoyun Zhang Shanghai Jiaotong University
• Xiao-ming Wu Sun Yat-sen University Macquarie University
• Chao Dong SIAT

Keywords

No keywords are indexed for this paper.