(Learning Texture Transformer Network for Image Super-Resolution)[https://openaccess.thecvf.com/content_CVPR_2020/html/Yang_Learning_Texture_Transformer_Network_for_Image_Super-Resolution_CVPR_2020_paper.html]
(Visual Transformers: Token-based Image Representation and Processing for Computer Vision)[https://arxiv.org/pdf/2006.03677.pdf] (知乎讨论)[https://www.zhihu.com/question/400733777/answer/1466879756]
(AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE)[https://openreview.net/pdf?id=YicbFdNTTy]
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
(ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness)[https://arxiv.org/abs/1811.12231]
Super-Resolution and Noise Reduction (Residual Channel Attention Generative Adversarial Network for Image Super-Resolution and Noise Reduction)[http://xxx.itp.ac.cn//pdf/2004.13674.pdf]
(NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results)[https://arxiv.org/abs/2005.01996]
(Frequency Separation for Real-World Super-Resolution)[http://xxx.itp.ac.cn/pdf/1911.07850.pdf]