# Understanding the Effective Receptive Field in Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1701.04128 · HTML: https://mlsanity.com/paper/1701.04128/

## Key facts

- Cited by 553 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2017.

## Built on by (most cited first, 30 of 553)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows](https://mlsanity.com/paper/2107.12571/) (2021)
- [End-to-end Interpretable Neural Motion Planner](https://mlsanity.com/paper/2101.06679/) (2021)
- [ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias](https://mlsanity.com/paper/2106.03348/) (2021)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [nnFormer: Interleaved Transformer for Volumetric Segmentation](https://mlsanity.com/paper/2109.03201/) (2021)
- [Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining](https://mlsanity.com/paper/2402.03302/) (2024)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [IntentNet: Learning to Predict Intention from Raw Sensor Data](https://mlsanity.com/paper/2101.07907/) (2021)
- [Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs](https://mlsanity.com/paper/2203.06717/) (2022)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model](https://mlsanity.com/paper/2208.03987/) (2022)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [Spherical Transformer for LiDAR-based 3D Recognition](https://mlsanity.com/paper/2303.12766/) (2023)
- [Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization](https://mlsanity.com/paper/2210.14457/) (2022)
- [ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond](https://mlsanity.com/paper/2202.10108/) (2022)
- [HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding](https://mlsanity.com/paper/2205.09753/) (2022)
- [Large Selective Kernel Network for Remote Sensing Object Detection](https://mlsanity.com/paper/2303.09030/) (2023)
- [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024)
- [Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data](https://mlsanity.com/paper/2402.05892/) (2024)

## Abstract (arXiv)

We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. We introduce the notion of an effective receptive field, and show that it both has a Gaussian distribution and only occupies a fraction of the full theoretical receptive field. We analyze the effective receptive field in several architecture designs, and the effect of nonlinear activations, dropout, sub-sampling and skip connections on it. This leads to suggestions for ways to address its tendency to be too small.