mlsanityData to 7 Oct 2026

Are we ready for a new paradigm shift? A Survey on Visual Deep MLP

arXiv 2111.04060 ↗First posted 7 Nov 2021cs.CVcited by 63

Not on the map. Why?

Abstract (arXiv)

Recently, the proposed deep MLP models have stirred up a lot of interest in the vision community. Historically, the availability of larger datasets combined with increased computing capacity leads to paradigm shifts. This review paper provides detailed discussions on whether MLP can be a new paradigm for computer vision. We compare the intrinsic connections and differences between convolution, self-attention mechanism, and Token-mixing MLP in detail. Advantages and limitations of Token-mixing MLP are provided, followed by careful analysis of recent MLP-like variants, from module design to network architecture, and their applications. In the GPU era, the locally and globally weighted summations are the current mainstreams, represented by the convolution and self-attention mechanism, as well as MLP. We suggest the further development of paradigm to be considered alongside the next-generation computing devices.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Builds on 113 of its 194 references that are in the map. First posted on arXiv 7 Nov 2021.

Builds on

113 of 194 references.

References · 113

  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. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  9. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  10. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  11. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  12. 2020End-to-End Object Detection with Transformerscited by 7,384
38 more
  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Mask R-CNNcited by 7,259
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2016Layer Normalizationcited by 5,579
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  10. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  11. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  12. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  13. 2014Going Deeper with Convolutionscited by 4,231
  14. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  15. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  16. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  17. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  18. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  19. 2018YOLOv3: An Incremental Improvementcited by 2,652
  20. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  21. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  22. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  23. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  24. 2019Searching for MobileNetV3cited by 1,984
  25. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  26. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  27. 2017Decoupled Weight Decay Regularizationcited by 1,722
  28. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  29. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  30. 2017Deformable Convolutional Networkscited by 1,481
  31. 2020Point Transformercited by 1,462
  32. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  33. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  34. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  35. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  36. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  37. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  38. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128

50 most cited of 113 All 113 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 9; 2023: 23; 2024: 11; 2025: 13; 2026: 5.

63 papers.

Sort:

By area:

  1. 2022Visual Attention Networkcited by 210
  2. 2023Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networkscited by 129
  3. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 74
  4. 2023LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzlescited by 41
  5. 2024Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registrationcited by 37
  6. 2022Multi-Task Learning with Multi-Query Transformer for Dense Predictioncited by 34
  7. 2021Augmenting Convolutional networks with attention-based aggregationcited by 29
  8. 2024When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Modelscited by 22
  9. 2023Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characterscited by 21
  10. 2025DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokenscited by 21
  11. 2023Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignmentcited by 19
  12. 2023A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Checkcited by 15
38 more
  1. 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learningcited by 14
  2. 2023MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entitiescited by 13
  3. 2022SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLPcited by 12
  4. 2023Strip-MLP: Efficient Token Interaction for Vision MLPcited by 12
  5. 2022Active Relation Discovery: Towards General and Label-aware Open Relation Extractioncited by 10
  6. 2024Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correctioncited by 9
  7. 2025Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flowcited by 9
  8. 2023Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inferencecited by 7
  9. 2025AdmTree: Compressing Lengthy Context with Adaptive Semantic Treescited by 7
  10. 2026EvoConfig: Self-Evolving Multi-Agent Systems for Efficient Autonomous Environment Configurationcited by 7
  11. 2021MLP Architectures for Vision-and-Language Modeling: An Empirical Studycited by 6
  12. 2023ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understandingcited by 6
  13. 2023Full-resolution MLPs Empower Medical Dense Predictioncited by 6
  14. 2026Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understandingcited by 6
  15. 2022Towards Attribute-Entangled Controllable Text Generation: A Pilot Study of Blessing Generationcited by 4
  16. 2023Multi-task Transformer with Relation-attention and Type-attention for Named Entity Recognitioncited by 4
  17. 2024Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Frameworkcited by 4
  18. 2024Hierarchical Associative Memory, Parallelized MLP-Mixer, and Symmetry Breakingcited by 4
  19. 2022Fast matrix multiplication for binary and ternary CNNs on ARM CPUcited by 3
  20. 2022Global Mixup: Eliminating Ambiguity with Clusteringcited by 3
  21. 2022Forecasting of depth and ego-motion with transformers and self-supervisioncited by 3
  22. 2023Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentationcited by 3
  23. 2023From Retrieval to Generation: Efficient and Effective Entity Set Expansioncited by 3
  24. 2023iMixer: hierarchical Hopfield network implies an invertible, implicit and iterative MLP-Mixercited by 3
  25. 2024Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansioncited by 3
  26. 2025MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuningcited by 3
  27. 2026TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoningcited by 3
  28. 2022A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Rankingcited by 2
  29. 2023Retrieval-Augmented Meta Learning for Low-Resource Text Classificationcited by 2
  30. 2023MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correctioncited by 2
  31. 2024UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entitiescited by 2
  32. 2025Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learningcited by 2
  33. 2023Computationally Efficient 3D MRI Reconstruction with Adaptive MLPcited by 1
  34. 2023Investigating Graph Structure Information for Entity Alignment with Dangling Casescited by 1
  35. 2023TriMLP: Revenge of a MLP-like Architecture in Sequential Recommendationcited by 1
  36. 2023Prompt Learning With Knowledge Memorizing Prototypes For Generalized Few-Shot Intent Detectioncited by 1
  37. 2025Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correctioncited by 1
  38. 2025Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detectioncited by 1

50 most cited of 63 All 63 (JSON)