mlsanityData to 14 Oct 2026

RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality

arXiv 2112.11081 ↗First posted 21 Dec 2021cs.CV cs.AI cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Compared to convolutional layers, fully-connected (FC) layers are better at modeling the long-range dependencies but worse at capturing the local patterns, hence usually less favored for image recognition. In this paper, we propose a methodology, Locality Injection, to incorporate local priors into an FC layer via merging the trained parameters of a parallel conv kernel into the FC kernel. Locality Injection can be viewed as a novel Structural Re-parameterization method since it equivalently converts the structures via transforming the parameters. Based on that, we propose a multi-layer-perceptron (MLP) block named RepMLP Block, which uses three FC layers to extract features, and a novel architecture named RepMLPNet. The hierarchical design distinguishes RepMLPNet from the other concurrently proposed vision MLPs. As it produces feature maps of different levels, it qualifies as a backbone model for downstream tasks like semantic segmentation. Our results reveal that 1) Locality Injection is a general methodology for MLP models; 2) RepMLPNet has favorable accuracy-efficiency trade-off compared to the other MLPs; 3) RepMLPNet is the first MLP that seamlessly transfer to Cityscapes semantic segmentation. The code and models are available at https://github.com/DingXiaoH/RepMLP.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 38 of its 47 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

38 of 47 references.

References · 38

  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. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  10. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  11. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  12. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
26 more
  1. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  2. 2017Non-local Neural Networkscited by 2,293
  3. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  4. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  6. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  7. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  8. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  9. 2020Designing Network Design Spacescited by 960
  10. 2018Rethinking the Value of Network Pruningcited by 599
  11. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  12. 2021Pay Attention to MLPscited by 368
  13. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 339
  14. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  15. 2019ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blockscited by 178
  16. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  17. 2015Fast Algorithms for Convolutional Neural Networkscited by 102
  18. 2013Fast Training of Convolutional Networks through FFTscited by 89
  19. 2021Diverse Branch Block: Building a Convolution as an Inception-like Unitcited by 87
  20. 2020ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgettingcited by 85
  21. 2021S2-MLP: Spatial-Shift MLP Architecture for Visioncited by 83
  22. 2019Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structurecited by 76
  23. 2019Global Sparse Momentum SGD for Pruning Very Deep Neural Networkscited by 70
  24. 2019Approximated Oracle Filter Pruning for Destructive CNN Width Optimizationcited by 35
  25. 2017MEC: Memory-efficient Convolution for Deep Neural Networkcited by 14
  26. 2021Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNNcited by 9

Built on by

Cited by year

Citing papers per year: 2022: 10; 2023: 10; 2024: 11; 2025: 1.

32 papers.

Sort:

By area:

  1. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  2. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142
  3. 2023Towards Efficient Visual Adaption via Structural Re-parameterizationcited by 73
  4. 2023UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognitioncited by 64
  5. 2022MogaNet: Multi-order Gated Aggregation Networkcited by 59
  6. 2022Can CNNs Be More Robust Than Transformers?cited by 38
  7. 2022Re-parameterizing Your Optimizers rather than Architecturescited by 35
  8. 2022Sequencer: Deep LSTM for Image Classificationcited by 23
  9. 2024Zero-shot Generalizable Incremental Learning for Vision-Language Object Detectioncited by 15
  10. 2023Unlocking Deterministic Robustness Certification on ImageNetcited by 13
  11. 2023RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixercited by 13
  12. 2024Toward a Holistic Evaluation of Robustness in CLIP Modelscited by 13
20 more
  1. 2023RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNetscited by 9
  2. 2022SinGRAV: Learning a Generative Radiance Volume from a Single Natural Scenecited by 8
  3. 2023Are Large Kernels Better Teachers than Transformers for ConvNets?cited by 8
  4. 2024Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representationscited by 8
  5. 2024Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalitiescited by 7
  6. 2022The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimescited by 6
  7. 2023FalconNet: Factorization for the Light-weight ConvNetscited by 6
  8. 2023Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splittingcited by 6
  9. 2024Aligning in a Compact Space: Contrastive Knowledge Distillation between Heterogeneous Architecturescited by 5
  10. 2024DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentationcited by 4
  11. 2022CM-MLP: Cascade Multi-scale MLP with Axial Context Relation Encoder for Edge Segmentation of Medical Imagecited by 2
  12. 2023Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Modelcited by 2
  13. 2024Conv-INR: Convolutional Implicit Neural Representation for Multimodal Visual Signalscited by 2
  14. 2024Reparameterized Multi-Resolution Convolutions for Long Sequence Modellingcited by 2
  15. 2023TriMLP: Revenge of a MLP-like Architecture in Sequential Recommendationcited by 1
  16. 2024Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignmentcited by 1
  17. 2025Semantic-Space-Intervened Diffusive Alignment for Visual Classificationcited by 1
  18. 2022A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentationcited by 0
  19. 2024RepAct: The Re-parameterizable Adaptive Activation Functioncited by 0
  20. 2024Interpolated-MLPs: Controllable Inductive Biascited by 0