arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.03364cs.CV
收藏

用于图像超分辨率的双聚合Transformer

Dual Aggregation Transformer for Image Super-Resolution

Shanghai Jiao Tong University(上海交通大学);ETH Zürich(苏黎世联邦理工学院);The University of Sydney(悉尼大学);Shanghai AI Laboratory(上海人工智能实验室)

Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong, Xiaokang Yang, Fisher Yu

AI总结:

本文提出双聚合Transformer(DAT),通过交替空间与通道自注意力实现块间特征聚合,并引入AIM和SGFN实现块内聚合,在图像超分辨率任务上超越现有方法。

摘要:

Transformer最近在包括图像超分辨率(SR)在内的低级视觉任务中获得了相当大的流行。这些网络沿不同维度(空间或通道)利用自注意力,并取得了令人印象深刻的性能。这启发我们在Transformer中结合这两个维度,以获得更强大的表示能力。基于上述思想,我们提出了一种新颖的Transformer模型,即双聚合Transformer(DAT),用于图像SR。我们的DAT以块间和块内的双重方式在空间和通道维度上聚合特征。具体来说,我们在连续的Transformer块中交替应用空间和通道自注意力。这种交替策略使DAT能够捕获全局上下文并实现块间特征聚合。此外,我们提出了自适应交互模块(AIM)和空间门控前馈网络(SGFN)来实现块内特征聚合。AIM从相应维度补充两种自注意力机制。同时,SGFN在前馈网络中引入了额外的非线性空间信息。大量实验表明,我们的DAT超越了当前方法。代码和模型可在https://github.com/zhengchen1999/DAT获取。

英文摘要:

Transformer has recently gained considerable popularity in low-level vision tasks, including image super-resolution (SR). These networks utilize self-attention along different dimensions, spatial or channel, and achieve impressive performance. This inspires us to combine the two dimensions in Transformer for a more powerful representation capability. Based on the above idea, we propose a novel Transformer model, Dual Aggregation Transformer (DAT), for image SR. Our DAT aggregates features across spatial and channel dimensions, in the inter-block and intra-block dual manner. Specifically, we alternately apply spatial and channel self-attention in consecutive Transformer blocks. The alternate strategy enables DAT to capture the global context and realize inter-block feature aggregation. Furthermore, we propose the adaptive interaction module (AIM) and the spatial-gate feed-forward network (SGFN) to achieve intra-block feature aggregation. AIM complements two self-attention mechanisms from corresponding dimensions. Meanwhile, SGFN introduces additional non-linear spatial information in the feed-forward network. Extensive experiments show that our DAT surpasses current methods. Code and models are obtainable at https://github.com/zhengchen1999/DAT.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑