arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.09735cs.CV
收藏

SRFormerV2:深入研究用于图像超分辨率的置换自注意力

SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution

Nankai University(南开大学);NUDT(国防科技大学)

Yupeng Zhou, Zhen Li, Chun-Le Guo, Li Liu, Ming-Ming Cheng, Qibin Hou

AI总结:

针对大窗口Transformer超分辨率模型计算开销高的问题,提出基于置换自注意力的SRFormer,平衡通道与空间信息,在更低参数量和计算量下性能优于SwinIR,扩展后的SRFormerV2达到当前最优水平。

摘要:

已有研究表明,增大基于Transformer的图像超分辨率模型(如SwinIR)的窗口尺寸可显著提升模型性能,但当窗口尺寸逐步增大时,计算开销也相当可观。本文提出SRFormer,这是一种简单却新颖的方法,既能享有大窗口自注意力的优势,又能带来更低的计算负担。SRFormer的核心是置换自注意力(permuted self-attention, PSA),它在自注意力的通道信息与空间信息之间取得了恰当平衡。在未添加任何额外技巧的情况下,我们的SRFormer在Urban100数据集上取得了33.86dB的PSNR指标,比SwinIR高0.46dB,且参数量与计算量更低。此外,我们还尝试通过进一步增大窗口尺寸和通道数来扩展模型规模,以探索基于Transformer的模型的潜力。实验表明,我们的扩展模型SRFormerV2能进一步提升效果,达到当前最优水平。我们希望这种简单有效的方法能为未来超分辨率模型设计的相关研究提供帮助。项目主页为https://z-yupeng.github.io/SRFormer/。

英文摘要:

Previous works have shown that increasing the window size for Transformer-based image super-resolution models (e.g., SwinIR) can significantly improve the model performance. Still, the computation overhead is also considerable when the window size gradually increases. In this paper, we present SRFormer, a simple but novel method that can enjoy the benefit of large window self-attention but introduces even less computational burden. The core of our SRFormer is the permuted self-attention (PSA), which strikes an appropriate balance between the channel and spatial information for self-attention. Without any bells and whistles, we show that our SRFormer achieves a 33.86dB PSNR score on the Urban100 dataset, which is 0.46dB higher than that of SwinIR but uses fewer parameters and computations. In addition, we also attempt to scale up the model by further enlarging the window size and channel numbers to explore the potential of Transformer-based models. Experiments show that our scaled model, named SRFormerV2, can further improve the results and achieves state-of-the-art. We hope our simple and effective approach could be useful for future research in super-resolution model design. The homepage is https://z-yupeng.github.io/SRFormer/.

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。

↑