Residential College | false |
Status | 已發表Published |
Implicit Prompt Learning for Image Denoising | |
Lu, Yao1; Jiang, Bo2; Lu, Guangming1; Zhang, Bob3 | |
2024 | |
Conference Name | 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024 |
Source Publication | Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence |
Pages | 4678-4686 |
Conference Date | 3-9 August 2024 |
Conference Place | Jeju, South Korea |
Publisher | International Joint Conferences on Artificial Intelligence |
Abstract | Recently, various deep denoising methods have been proposed to solve the insufficient feature problem in image denoising. These methods can be mainly classified into two categories: (1) Injecting learnable tensors into denoising backbone to supplement feature, which is effective to some extent but may cause serious over-fitting. (2) Using diverse natural images from large image datasets to synthesize noisy images and pre-train denoising models, which can bring model generalization but require large model size and expensive training costs. To address these issues, this paper proposes Implicit Prompt Learning for Image Denoising (IPLID) method to flexibly generate adaptive prompts without meticulously designing them. Specifically, we first introduce an efficient Linear Prompt (LP) block with ultra-few parameters to produce dynamic prompts for both different stages and samples in denoising procedure. We further propose an efficient Compact Feature Fusion (CFF) block to process previous multi-level prompted denoising feature to reconstruct the denoising images. Finally, to further efficiently and effectively produce satisfactory prompt and denoising performance, a Gradient Accumulation (GA) learning scheme is proposed. Experiments on multiple benchmarks showed that the proposed IPLID achieves competitive results with only 1 percent of pre-trained backbone parameters, outperforming classical denoising methods in both efficiency and quality of restored images. |
Keyword | Machine Learning Knowledge-aided Learning |
DOI | 10.24963/ijcai.2024/517 |
URL | View the original |
Language | 英語English |
Scopus ID | 2-s2.0-85204307488 |
Fulltext Access | |
Citation statistics | |
Document Type | Conference paper |
Collection | Faculty of Science and Technology DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE |
Corresponding Author | Jiang, Bo; Lu, Guangming |
Affiliation | 1.Department of Computer Science, Harbin Institute of Technology, Shenzhen, China 2.College of Mechanical and Electronic Engineering, Northwest A&F University, China 3.Department of Computer and Information Science, University of Macau, Macao |
Recommended Citation GB/T 7714 | Lu, Yao,Jiang, Bo,Lu, Guangming,et al. Implicit Prompt Learning for Image Denoising[C]:International Joint Conferences on Artificial Intelligence, 2024, 4678-4686. |
APA | Lu, Yao., Jiang, Bo., Lu, Guangming., & Zhang, Bob (2024). Implicit Prompt Learning for Image Denoising. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 4678-4686. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment