# Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs

arXiv: https://arxiv.org/abs/2203.06717 · HTML: https://mlsanity.com/paper/2203.06717/

## Key facts

- Cited by 155 papers in the map (data through 14 Oct 2026).
- Builds on 109 of its 126 references that are in the map.
- First posted on arXiv 13 Mar 2022.

## Builds on (most cited first, 30 of 109)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)

## Built on by (most cited first, 30 of 155)

- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [Meta-Transformer: A Unified Framework for Multimodal Learning](https://mlsanity.com/paper/2307.10802/) (2023)
- [MetaFormer Baselines for Vision](https://mlsanity.com/paper/2210.13452/) (2022)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [Revealing the Dark Secrets of Masked Image Modeling](https://mlsanity.com/paper/2205.13543/) (2022)
- [ConvMAE: Masked Convolution Meets Masked Autoencoders](https://mlsanity.com/paper/2205.03892/) (2022)
- [HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions](https://mlsanity.com/paper/2207.14284/) (2022)
- [Large Selective Kernel Network for Remote Sensing Object Detection](https://mlsanity.com/paper/2303.09030/) (2023)
- [3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2209.15076/) (2022)
- [Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling](https://mlsanity.com/paper/2301.03580/) (2023)
- [What Makes Convolutional Models Great on Long Sequence Modeling?](https://mlsanity.com/paper/2210.09298/) (2022)
- [Towards Efficient Visual Adaption via Structural Re-parameterization](https://mlsanity.com/paper/2302.08106/) (2023)
- [LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs](https://mlsanity.com/paper/2206.10555/) (2022)
- [A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift](https://mlsanity.com/paper/2206.10810/) (2022)
- [Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification](https://mlsanity.com/paper/2210.12843/) (2022)
- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [TransNeXt: Robust Foveal Visual Perception for Vision Transformers](https://mlsanity.com/paper/2311.17132/) (2023)
- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [ShuffleMixer: An Efficient ConvNet for Image Super-Resolution](https://mlsanity.com/paper/2205.15175/) (2022)
- [Adaptive Frequency Filters As Efficient Global Token Mixers](https://mlsanity.com/paper/2307.14008/) (2023)
- [Image as Set of Points](https://mlsanity.com/paper/2303.01494/) (2023)
- [EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction](https://mlsanity.com/paper/2205.14756/) (2022)
- [U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration?](https://mlsanity.com/paper/2208.04939/) (2022)
- [Can CNNs Be More Robust Than Transformers?](https://mlsanity.com/paper/2206.03452/) (2022)
- [Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention](https://mlsanity.com/paper/2304.04237/) (2023)
- [Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2206.14383/) (2022)
- [Re-parameterizing Your Optimizers rather than Architectures](https://mlsanity.com/paper/2205.15242/) (2022)

## Abstract (arXiv)

We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small kernels could be a more powerful paradigm. We suggested five guidelines, e.g., applying re-parameterized large depth-wise convolutions, to design efficient high-performance large-kernel CNNs. Following the guidelines, we propose RepLKNet, a pure CNN architecture whose kernel size is as large as 31x31, in contrast to commonly used 3x3. RepLKNet greatly closes the performance gap between CNNs and ViTs, e.g., achieving comparable or superior results than Swin Transformer on ImageNet and a few typical downstream tasks, with lower latency. RepLKNet also shows nice scalability to big data and large models, obtaining 87.8% top-1 accuracy on ImageNet and 56.0% mIoU on ADE20K, which is very competitive among the state-of-the-arts with similar model sizes. Our study further reveals that, in contrast to small-kernel CNNs, large-kernel CNNs have much larger effective receptive fields and higher shape bias rather than texture bias. Code & models at https://github.com/megvii-research/RepLKNet.