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 2104.02555cs.CVcs.LGeess.IV
收藏

傅立叶图像Transformer

Fourier Image Transformer

FMI for Biomedical Research(FMI生物医学研究所);Fondazione Human Technopole(人类技术基金会)

Tim-Oliver Buchholz, Florian Jug

摘要:

Transformer架构在NLP任务上表现出惊人的性能,最近也被用于图像完成或图像分类等任务。在这里,我们建议使用顺序图像表示,其中完整序列的每个前缀以降低的分辨率描述整个图像。使用这样的傅立叶域编码(FDE),自回归图像完成任务等同于在给定低分辨率输入的情况下预测更高分辨率的输出。此外,我们表明,一个编码器-解码器设置可以用来查询任意傅立叶系数给定一组傅立叶域的意见。我们证明了这种方法在计算机断层扫描(CT)图像重建的背景下的实用性。总之,我们证明了傅立叶图像Transformer(FIT)可以用于解决傅立叶空间中的相关图像分析任务,这是卷积架构固有地无法访问的域。

英文摘要:

Transformer architectures show spectacular performance on NLP tasks and have recently also been used for tasks such as image completion or image classification. Here we propose to use a sequential image representation, where each prefix of the complete sequence describes the whole image at reduced resolution. Using such Fourier Domain Encodings (FDEs), an auto-regressive image completion task is equivalent to predicting a higher resolution output given a low-resolution input. Additionally, we show that an encoder-decoder setup can be used to query arbitrary Fourier coefficients given a set of Fourier domain observations. We demonstrate the practicality of this approach in the context of computed tomography (CT) image reconstruction. In summary, we show that Fourier Image Transformer (FIT) can be used to solve relevant image analysis tasks in Fourier space, a domain inherently inaccessible to convolutional architectures.

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。

↑