VALSE

VALSE 首页 活动通知 查看内容

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 ...

2024-8-27 11:00| 发布者: 程一-计算所| 查看: 163| 评论: 0

摘要: 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) ...

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)


活动参与方式

1、VALSE每周举行的Webinar活动依托B站直播平台进行,欢迎在B站搜索VALSE_Webinar关注我们!

直播地址:

https://live.bilibili.com/22300737;

历史视频观看地址:

https://space.bilibili.com/562085182/ 


2、VALSE Webinar活动通常每周三晚上20:00进行,但偶尔会因为讲者时区问题略有调整,为方便您参加活动,请关注VALSE微信公众号:valse_wechat 或加入VALSE QQ T群,群号:863867505);


*注:申请加入VALSE QQ群时需验证姓名、单位和身份缺一不可。入群后,请实名,姓名身份单位。身份:学校及科研单位人员T;企业研发I;博士D;硕士M。


3、VALSE微信公众号一般会在每周四发布下一周Webinar报告的通知。


4您也可以通过访问VALSE主页:http://valser.org/ 直接查看Webinar活动信息。Webinar报告的PPT(经讲者允许后),会在VALSE官网每期报告通知的最下方更新。


小黑屋|手机版|Archiver|Vision And Learning SEminar

GMT+8, 2024-10-13 15:30 , Processed in 0.012529 second(s), 14 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.

返回顶部