# Dead Pixel Test Using Effective Receptive Field

arXiv: https://arxiv.org/abs/2108.13576 · HTML: https://mlsanity.com/paper/2108.13576/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 54 references that are in the map.
- First posted on arXiv 31 Aug 2021.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [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)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)

## Built on by (most cited first, 18 of 18)

- [Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs](https://mlsanity.com/paper/2203.06717/) (2022)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [TransNeXt: Robust Foveal Visual Perception for Vision Transformers](https://mlsanity.com/paper/2311.17132/) (2023)
- [RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer](https://mlsanity.com/paper/2304.05659/) (2023)
- [SBSS: Stacking-Based Semantic Segmentation Framework for Very High Resolution Remote Sensing Image](https://mlsanity.com/paper/2212.07623/) (2022)
- [Vision Transformers in Medical Imaging: A Review](https://mlsanity.com/paper/2211.10043/) (2022)
- [Are Large Kernels Better Teachers than Transformers for ConvNets?](https://mlsanity.com/paper/2305.19412/) (2023)
- [Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields](https://mlsanity.com/paper/2305.04722/) (2023)
- [DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2409.15801/) (2024)
- [MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detection](https://mlsanity.com/paper/2405.09933/) (2024)
- [HyenaPixel: Global Image Context with Convolutions](https://mlsanity.com/paper/2402.19305/) (2024)
- [COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking](https://mlsanity.com/paper/2504.01321/) (2025)
- [Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks](https://mlsanity.com/paper/2307.14179/) (2023)
- [Fast-ParC: Capturing Position Aware Global Feature for ConvNets and ViTs](https://mlsanity.com/paper/2210.04020/) (2022)
- [Towards Optimal Aggregation of Varying Range Dependencies in Haze Removal](https://mlsanity.com/paper/2408.12317/) (2024)
- [IConv: Focusing on Local Variation with Channel Independent Convolution for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2509.20783/) (2025)
- [ACFormer: Mitigating Non-linearity with Auto Convolutional Encoder for Time Series Forecasting](https://mlsanity.com/paper/2601.20611/) (2026)
- [From Local Training to Large-Scale Mapping: A Comparative Assessment of Machine Learning and Deep Learning for Transferable Satellite-Derived Bathymetry](https://mlsanity.com/paper/2606.02764/) (2026)

## Abstract (arXiv)

Deep neural networks have been used in various fields, but their internal behavior is not well known. In this study, we discuss two counterintuitive behaviors of convolutional neural networks (CNNs). First, we evaluated the size of the receptive field. Previous studies have attempted to increase or control the size of the receptive field. However, we observed that the size of the receptive field does not describe the classification accuracy. The size of the receptive field would be inappropriate for representing superiority in performance because it reflects only depth or kernel size and does not reflect other factors such as width or cardinality. Second, using the effective receptive field, we examined the pixels contributing to the output. Intuitively, each pixel is expected to equally contribute to the final output. However, we found that there exist pixels in a partially dead state with little contribution to the output. We reveal that the reason for this lies in the architecture of CNN and discuss solutions to reduce the phenomenon. Interestingly, for general classification tasks, the existence of dead pixels improves the training of CNNs. However, in a task that captures small perturbation, dead pixels degrade the performance. Therefore, the existence of these dead pixels should be understood and considered in practical applications of CNN.