Timezone: »

Random Shuffle Transformer for Image Restoration
Jie Xiao · Xueyang Fu · Man Zhou · Hongjian Liu · Zheng-Jun Zha

Tue Jul 25 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #202

Non-local interactions play a vital role in boosting performance for image restoration. However, local window Transformer has been preferred due to its efficiency for processing high-resolution images. The superiority in efficiency comes at the cost of sacrificing the ability to model non-local interactions. In this paper, we present that local window Transformer can also function as modeling non-local interactions. The counterintuitive function is based on the permutation-equivariance of self-attention. The basic principle is quite simple: by randomly shuffling the input, local self-attention also has the potential to model non-local interactions without introducing extra parameters. Our random shuffle strategy enjoys elegant theoretical guarantees in extending the local scope. The resulting Transformer dubbed ShuffleFormer is capable of processing high-resolution images efficiently while modeling non-local interactions. Extensive experiments demonstrate the effectiveness of ShuffleFormer across a variety of image restoration tasks, including image denoising, deraining, and deblurring. Code is available at https://github.com/jiexiaou/ShuffleFormer.

Author Information

Jie Xiao (University of Science and Technology of China)
Xueyang Fu (University of Science and Technology of China)
Man Zhou
Hongjian Liu (University of Science and Technology of China)
Zheng-Jun Zha (University of Science and Technology of China)

More from the Same Authors