mlsanityData to 7 Oct 2026

Fourier Image Transformer

arXiv 2104.02555 ↗First posted 6 Apr 2021cs.CV cs.LG eess.IVcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 18 of its 30 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

18 of 30 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  6. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,935
  7. 2020Reformer: The Efficient Transformercited by 1,658
  8. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  9. 2018Image Transformercited by 770
  10. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  11. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  12. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
6 more
  1. 2018Deep Learning for Classical Japanese Literaturecited by 415
  2. 2017Learned Primal-dual Reconstructioncited by 251
  3. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  4. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  5. 2017Model based learning for accelerated, limited-view 3D photoacoustic tomographycited by 45
  6. 2019The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methodscited by 12

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 3; 2024: 5.

12 papers.

  1. 2022Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectivescited by 32
  2. 2024DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Spacecited by 32
  3. 2024Visual Fourier Prompt Tuningcited by 30
  4. 2024DiJiang: Efficient Large Language Models through Compact Kernelizationcited by 15
  5. 2024EmMixformer: Mix transformer for eye movement recognitioncited by 9
  6. 2023Efficiency 360: Efficient Vision Transformerscited by 6
  7. 2021Deep Microlocal Reconstruction for Limited-Angle Tomographycited by 4
  8. 2023Diagnostic Spatio-temporal Transformer with Faithful Encodingcited by 3
  9. 2024Discrete Cosine Transform Based Decorrelated Attention for Vision Transformerscited by 2
  10. 2021FNetAR: Mixing Tokens with Autoregressive Fourier Transformscited by 1
  11. 2022Contextual Learning in Fourier Complex Field for VHR Remote Sensing Imagescited by 1
  12. 2023TD-Net: A Tri-domain network for sparse-view CT reconstructioncited by 0