# Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network

arXiv: https://arxiv.org/abs/1703.02719 · HTML: https://mlsanity.com/paper/1703.02719/

## Key facts

- Cited by 208 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2017.

## Built on by (most cited first, 30 of 208)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.03024/) (2021)
- [Towards Multi-spatiotemporal-scale Generalized PDE Modeling](https://mlsanity.com/paper/2209.15616/) (2022)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs](https://mlsanity.com/paper/2203.06717/) (2022)
- [Camouflaged Object Segmentation with Distraction Mining](https://mlsanity.com/paper/2104.10475/) (2021)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [Sinkformers: Transformers with Doubly Stochastic Attention](https://mlsanity.com/paper/2110.11773/) (2021)
- [Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction](https://mlsanity.com/paper/2103.12091/) (2021)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation](https://mlsanity.com/paper/2212.04497/) (2022)
- [ConvMAE: Masked Convolution Meets Masked Autoencoders](https://mlsanity.com/paper/2205.03892/) (2022)
- [FocalClick: Towards Practical Interactive Image Segmentation](https://mlsanity.com/paper/2204.02574/) (2022)
- [SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2311.15537/) (2023)
- [3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2209.15076/) (2022)
- [Large Scale Visual Food Recognition](https://mlsanity.com/paper/2103.16107/) (2021)
- [Representation Compensation Networks for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.05402/) (2022)
- [LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs](https://mlsanity.com/paper/2206.10555/) (2022)
- [FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes](https://mlsanity.com/paper/2110.08059/) (2021)
- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition](https://mlsanity.com/paper/2311.15599/) (2023)
- [FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models](https://mlsanity.com/paper/2310.15160/) (2023)
- [Applications of Deep Learning in Fundus Images: A Review](https://mlsanity.com/paper/2101.09864/) (2021)
- [Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation](https://mlsanity.com/paper/2108.02376/) (2021)

## Abstract (arXiv)

One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational complexity. However, in the field of semantic segmenta- tion, where we need to perform dense per-pixel prediction, we find that the large kernel (and effective receptive field) plays an important role when we have to perform the clas- sification and localization tasks simultaneously. Following our design principle, we propose a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation. We also suggest a residual-based boundary refinement to further refine the ob- ject boundaries. Our approach achieves state-of-art perfor- mance on two public benchmarks and significantly outper- forms previous results, 82.2% (vs 80.2%) on PASCAL VOC 2012 dataset and 76.9% (vs 71.8%) on Cityscapes dataset.