Abstract
Recently, transformer-based models have achieved significant success in various computer vision tasks, with the attention-based token mixer module commonly believed to be the key factor. However, further research has shown that the attention-based token mixer module in transformers can be replaced by other methods, such as spatial multilayer perceptrons (MLPs) or Fourier transforms, to mix information between different tokens without sacrificing performance. Therefore, some have raised whether the success of transformers and its variants is not solely due to the attention-based token mixer module but rather to other factors. In a recent paper titled 'PoolFormer' the authors demonstrated that using a simple spatial pooling operation instead of the attention module in transformers can achieve competitive performance in object detection vision tasks. Based on this finding, we propose a low-computation model for image denoising based on the PoolFormer and an MLP + CNN Transformer decoder for image restoration. By reducing the computational complexity brought by the token mixer, the model still achieves a good peak signal-to-noise ratio (PSNR) in grayscale as well as in color image denoising. This suggests that, in low-level vision tasks such as denoising, simple attention modules can also achieve good results, particularly in grayscale image denoising.
Original language | English |
---|---|
Title of host publication | Proceedings - 2023 6th International Symposium on Computer, Consumer and Control, IS3C 2023 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 40-43 |
Number of pages | 4 |
ISBN (Electronic) | 9798350301953 |
DOIs | |
State | Published - 2023 |
Event | 6th International Symposium on Computer, Consumer and Control, IS3C 2023 - Taichung City, Taiwan Duration: 30 06 2023 → 03 07 2023 |
Publication series
Name | Proceedings - 2023 6th International Symposium on Computer, Consumer and Control, IS3C 2023 |
---|
Conference
Conference | 6th International Symposium on Computer, Consumer and Control, IS3C 2023 |
---|---|
Country/Territory | Taiwan |
City | Taichung City |
Period | 30/06/23 → 03/07/23 |
Bibliographical note
Publisher Copyright:© 2023 IEEE.