VALSE 论文速览 第191期：面向图像复原问题的对比学习通用框架 ...

论文题目：

Learning from History:Task-agnostic Model Contrastive Learning for Image Restoration

作者列表：

吴刚 (哈尔滨工业大学)、江俊君 (哈尔滨工业大学)、江奎 (哈尔滨工业大学)、刘贤明 (哈尔滨工业大学)

B站观看网址：

https://www.bilibili.com/video/BV1qS421R7mn/

论文摘要：

Contrastive learning has emerged as a prevailing paradigm for high-level vision tasks, which, by introducing properly negative samples, has also been exploited for low-level vision tasks to achieve a compact optimization space to account for their ill-posed nature. However, existing methods rely on manually predefined and task-oriented negatives, which often exhibit pronounced task-specific biases. To address this challenge, our paper introduces an innovative method termed 'learning from history', which dynamically generates negative samples from the target model itself. Our approach, named Model Contrastive Learning for Image Restoration (MCLIR), rejuvenates latency models as negative models, making it compatible with diverse image restoration tasks. We propose the Self-Prior guided Negative loss (SPN) to enable it. This approach significantly enhances existing models when retrained with the proposed model contrastive paradigm. The results show significant improvements in image restoration across various tasks and architectures. For example, models retrained with SPN outperform the original FFANet and DehazeFormer by 3.41 dB and 0.57 dB on the RESIDE indoor dataset for image dehazing. Similarly, they achieve notable improvements of 0.47 dB on SPA-Data over IDT for image deraining and 0.12 dB on Manga109 for a 4× scale super-resolution over lightweight SwinIR, respectively.

参考文献：

[1] Gang Wu, Junjun Jiang, Kui Jiang, and Xianming Liu, “Learning from history: Task-agnostic model contrastive learning for image restoration,” iAssociation for the Advance of Artificial Intelligence (AAAI), 2024.

论文链接：

[https://arxiv.org/abs/2309.06023]

代码链接：

[https://github.com/Aitical/MCLIR]

视频讲者简介：

吴刚，哈尔滨工业大学博士生，江俊君教授团队。研究方向为底层视觉图像复原任务和自监督表示学习。

个人主页：

https://github.com/Aitical

特别鸣谢本次论文速览主要组织者：

月度轮值AC：傅雪阳 (中国科学技术大学)