mlsanityData to 14 Oct 2026

AFIDAF: Alternating Fourier and Image Domain Adaptive Filters as an Efficient Alternative to Attention in ViTs

arXiv 2407.12217 ↗First posted 16 Jul 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose and demonstrate an alternating Fourier and image domain filtering approach for feature extraction as an efficient alternative to build a vision backbone without using the computationally intensive attention. The performance among the lightweight models reaches the state-of-the-art level on ImageNet-1K classification, and improves downstream tasks on object detection and segmentation consistently as well. Our approach also serves as a new tool to compress vision transformers (ViTs).

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 40 of its 48 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

40 of 48 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  8. 2022A ConvNet for the 2020scited by 3,579
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  11. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  12. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
28 more
  1. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  2. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  3. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  4. 2021Multiscale Vision Transformerscited by 897
  5. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  6. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  7. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  8. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  9. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  10. 2021FNet: Mixing Tokens with Fourier Transformscited by 347
  11. 2021Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformerscited by 248
  12. 2021Co-Scale Conv-Attentional Image Transformerscited by 224
  13. 2022Visual Attention Networkcited by 210
  14. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  15. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  16. 2022EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applicationscited by 121
  17. 2022Rethinking Vision Transformers for MobileNet Size and Speedcited by 121
  18. 2022EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformerscited by 116
  19. 2021Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformercited by 115
  20. 2024MobileNetV4 -- Universal Models for the Mobile Ecosystemcited by 99
  21. 2022Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognitioncited by 81
  22. 2022Fast Vision Transformers with HiLo Attentioncited by 78
  23. 2023SpectFormer: Frequency and Attention is what you need in a Vision Transformercited by 48
  24. 2022MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Modelscited by 47
  25. 2023Adaptive Frequency Filters As Efficient Global Token Mixerscited by 45
  26. 2022MixFormer: Mixing Features across Windows and Dimensionscited by 43
  27. 2021Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attentioncited by 36
  28. 2019AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networkscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026VideoSEMA: a scalable and efficient Mamba-like attention for video understandingcited by 0