# Selective Kernel Networks

arXiv: https://arxiv.org/abs/1903.06586 · HTML: https://mlsanity.com/paper/1903.06586/

## Key facts

- Cited by 403 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2019.

## Built on by (most cited first, 30 of 403)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [Scaling Local Self-Attention for Parameter Efficient Visual Backbones](https://mlsanity.com/paper/2103.12731/) (2021)
- [Vision Transformers are Robust Learners](https://mlsanity.com/paper/2105.07581/) (2021)
- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [Revisiting ResNets: Improved Training and Scaling Strategies](https://mlsanity.com/paper/2103.07579/) (2021)
- [Learning Enriched Features for Fast Image Restoration and Enhancement](https://mlsanity.com/paper/2205.01649/) (2022)
- [Efficient Self-supervised Vision Transformers for Representation Learning](https://mlsanity.com/paper/2106.09785/) (2021)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [Large Selective Kernel Network for Remote Sensing Object Detection](https://mlsanity.com/paper/2303.09030/) (2023)
- [Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures](https://mlsanity.com/paper/2403.02308/) (2024)
- [Contextual Transformer Networks for Visual Recognition](https://mlsanity.com/paper/2107.12292/) (2021)
- [Three things everyone should know about Vision Transformers](https://mlsanity.com/paper/2203.09795/) (2022)
- [You Only Learn One Representation: Unified Network for Multiple Tasks](https://mlsanity.com/paper/2105.04206/) (2021)
- [Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion](https://mlsanity.com/paper/2203.09780/) (2022)
- [RigNet: Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2107.13802/) (2021)
- [Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2203.00259/) (2022)
- [ResT: An Efficient Transformer for Visual Recognition](https://mlsanity.com/paper/2105.13677/) (2021)
- [Changer: Feature Interaction is What You Need for Change Detection](https://mlsanity.com/paper/2209.08290/) (2022)
- [ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection](https://mlsanity.com/paper/2308.07504/) (2023)
- [On the Integration of Self-Attention and Convolution](https://mlsanity.com/paper/2111.14556/) (2021)
- [Learning Normal Dynamics in Videos with Meta Prototype Network](https://mlsanity.com/paper/2104.06689/) (2021)

## Abstract (arXiv)

In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size of visual cortical neurons are modulated by the stimulus, which has been rarely considered in constructing CNNs. We propose a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information. A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer. Multiple SK units are stacked to a deep network termed Selective Kernel Networks (SKNets). On the ImageNet and CIFAR benchmarks, we empirically show that SKNet outperforms the existing state-of-the-art architectures with lower model complexity. Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their receptive field sizes according to the input. The code and models are available at https://github.com/implus/SKNet.