mlsanityData to 7 Oct 2026

Mixer is more than just a model

arXiv 2402.18007 ↗First posted 28 Feb 2024cs.LG cs.AI cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, MLP structures have regained popularity, with MLP-Mixer standing out as a prominent example. In the field of computer vision, MLP-Mixer is noted for its ability to extract data information from both channel and token perspectives, effectively acting as a fusion of channel and token information. Indeed, Mixer represents a paradigm for information extraction that amalgamates channel and token information. The essence of Mixer lies in its ability to blend information from diverse perspectives, epitomizing the true concept of "mixing" in the realm of neural network architectures. Beyond channel and token considerations, it is possible to create more tailored mixers from various perspectives to better suit specific task requirements. This study focuses on the domain of audio recognition, introducing a novel model named Audio Spectrogram Mixer with Roll-Time and Hermit FFT (ASM-RH) that incorporates insights from both time and frequency domains. Experimental results demonstrate that ASM-RH is particularly well-suited for audio data and yields promising outcomes across multiple classification tasks. The models and optimal weights files will be published.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 28 references that are in the map. First posted on arXiv 28 Feb 2024.

Builds on

24 of 28 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  6. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  7. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  8. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
  9. 2021AST: Audio Spectrogram Transformercited by 634
  10. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  11. 2021Pay Attention to MLPscited by 367
  12. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
12 more
  1. 2021SSAST: Self-Supervised Audio Spectrogram Transformercited by 166
  2. 2017Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutionscited by 93
  3. 2021S2-MLP: Spatial-Shift MLP Architecture for Visioncited by 83
  4. 2023MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixingcited by 52
  5. 2023Adaptive Frequency Filters As Efficient Global Token Mixerscited by 45
  6. 2024How Can Large Language Models Understand Spatial-Temporal Data?cited by 31
  7. 2022When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanismcited by 30
  8. 2021ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognitioncited by 29
  9. 2018Constructing Fast Network through Deconstruction of Convolutioncited by 24
  10. 2022Active Token Mixercited by 6
  11. 2023FlexiAST: Flexibility is What AST Needscited by 4
  12. 2024ASM: Audio Spectrogram Mixercited by 1

Built on by

Not cited yet.