mlsanityData to 7 Oct 2026

Brain-inspired Multilayer Perceptron with Spiking Neurons

arXiv 2203.14679 ↗First posted 28 Mar 2022cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Recently, Multilayer Perceptron (MLP) becomes the hotspot in the field of computer vision tasks. Without inductive bias, MLPs perform well on feature extraction and achieve amazing results. However, due to the simplicity of their structures, the performance highly depends on the local features communication machenism. To further improve the performance of MLP, we introduce information communication mechanisms from brain-inspired neural networks. Spiking Neural Network (SNN) is the most famous brain-inspired neural network, and achieve great success on dealing with sparse data. Leaky Integrate and Fire (LIF) neurons in SNNs are used to communicate between different time steps. In this paper, we incorporate the machanism of LIF neurons into the MLP models, to achieve better accuracy without extra FLOPs. We propose a full-precision LIF operation to communicate between patches, including horizontal LIF and vertical LIF in different directions. We also propose to use group LIF to extract better local features. With LIF modules, our SNN-MLP model achieves 81.9%, 83.3% and 83.5% top-1 accuracy on ImageNet dataset with only 4.4G, 8.5G and 15.2G FLOPs, respectively, which are state-of-the-art results as far as we know.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 46 of its 61 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

46 of 61 references.

References · 46

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2017Mask R-CNNcited by 7,259
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  10. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  11. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  12. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
34 more
  1. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  2. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  3. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  4. 2020Designing Network Design Spacescited by 954
  5. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  6. 2020Pre-Trained Image Processing Transformercited by 891
  7. 2021Transformer in Transformercited by 632
  8. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  9. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  10. 2020ResNeSt: Split-Attention Networkscited by 445
  11. 2021Pay Attention to MLPscited by 367
  12. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  13. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  14. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  15. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 261
  16. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  17. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
  18. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 174
  19. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 142
  20. 2020Disentangled Non-Local Neural Networkscited by 132
  21. 2020Lite Transformer with Long-Short Range Attentioncited by 127
  22. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  23. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
  24. 2021Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognitioncited by 103
  25. 2021AS-MLP: An Axial Shifted MLP Architecture for Visioncited by 101
  26. 2021S2-MLP: Spatial-Shift MLP Architecture for Visioncited by 83
  27. 2021Hire-MLP: Vision MLP via Hierarchical Rearrangementcited by 66
  28. 2021An Image Patch is a Wave: Phase-Aware Vision MLPcited by 61
  29. 2021Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentationcited by 54
  30. 2019Adaptive Context Network for Scene Parsingcited by 51
  31. 2020Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differencescited by 39
  32. 2021A Spiking Neural Network for Image Segmentationcited by 27
  33. 2018Spiking Deep Residual Networkcited by 18
  34. 2018Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communicationcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 7; 2024: 2; 2025: 2.

16 papers.

Sort:

By area:

  1. 2022BALF: Simple and Efficient Blur Aware Local Feature Detectorcited by 34
  2. 2023Direct Learning-Based Deep Spiking Neural Networks: A Reviewcited by 31
  3. 2023Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inferencecited by 7
  4. 2023Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networkscited by 7
  5. 2023Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representationcited by 6
  6. 2023Deep Multi-Threshold Spiking-UNet for Image Processingcited by 5
  7. 2022A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learningcited by 4
  8. 2023Dynamic Mobile-Former: Strengthening Dynamic Convolution with Attention and Residual Connection in Kernel Spacecited by 2
  9. 2024Spiking GS: Towards High-Accuracy and Low-Cost Surface Reconstruction via Spiking Neuron-based Gaussian Splattingcited by 2
  10. 2025Edge Intelligence with Spiking Neural Networkscited by 2
  11. 2022Event-Driven Tactile Learning with Location Spiking Neuronscited by 1
  12. 2023EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attentioncited by 1
4 more
  1. 2025U-Net-Like Spiking Neural Networks for Single Image Dehazingcited by 1
  2. 2022Improved Image Classification with Token Fusioncited by 0
  3. 2022Boost Event-Driven Tactile Learning with Location Spiking Neuronscited by 0
  4. 2024Training a General Spiking Neural Network with Improved Efficiency and Minimum Latencycited by 0