# On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification

arXiv: https://arxiv.org/abs/2106.07091 · HTML: https://mlsanity.com/paper/2106.07091/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 55 references that are in the map.
- First posted on arXiv 13 Jun 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [Liquid Time-constant Networks](https://mlsanity.com/paper/2006.04439/) (2020)
- [Scale-Aware Trident Networks for Object Detection](https://mlsanity.com/paper/1901.01892/) (2019)
- [Learning long-range spatial dependencies with horizontal gated-recurrent units](https://mlsanity.com/paper/1805.08315/) (2018)
- [Non-linear Convolution Filters for CNN-based Learning](https://mlsanity.com/paper/1708.07038/) (2017)
- [Structured Receptive Fields in CNNs](https://mlsanity.com/paper/1605.02971/) (2016)
- [Task-Driven Convolutional Recurrent Models of the Visual System](https://mlsanity.com/paper/1807.00053/) (2018)
- [Kervolutional Neural Networks](https://mlsanity.com/paper/1904.03955/) (2019)
- [Adversarial Training is Not Ready for Robot Learning](https://mlsanity.com/paper/2103.08187/) (2021)
- [Correspondence of Deep Neural Networks and the Brain for Visual Textures](https://mlsanity.com/paper/1806.02888/) (2018)
- [Worm-level Control through Search-based Reinforcement Learning](https://mlsanity.com/paper/1711.03467/) (2017)

## Built on by (most cited first, 15 of 15)

- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [GoTube: Scalable Stochastic Verification of Continuous-Depth Models](https://mlsanity.com/paper/2107.08467/) (2021)
- [Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels](https://mlsanity.com/paper/2401.14469/) (2024)
- [Interactive Analysis of CNN Robustness](https://mlsanity.com/paper/2110.07667/) (2021)
- [Explaining V1 Properties with a Biologically Constrained Deep Learning Architecture](https://mlsanity.com/paper/2305.11275/) (2023)
- [Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields](https://mlsanity.com/paper/2401.10178/) (2024)
- [The Master Key Filters Hypothesis: Deep Filters Are General](https://mlsanity.com/paper/2412.16751/) (2024)
- [IB-U-Nets: Improving medical image segmentation tasks with 3D Inductive Biased kernels](https://mlsanity.com/paper/2210.15949/) (2022)
- [Interpreting Neural Policies with Disentangled Tree Representations](https://mlsanity.com/paper/2210.06650/) (2022)
- [Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition](https://mlsanity.com/paper/2306.13783/) (2023)
- [S3TC: Spiking Separated Spatial and Temporal Convolutions with Unsupervised STDP-based Learning for Action Recognition](https://mlsanity.com/paper/2309.12761/) (2023)
- [The Quest for Universal Master Key Filters in DS-CNNs](https://mlsanity.com/paper/2509.11711/) (2025)
- [3D-OOCS: Learning Prostate Segmentation with Inductive Bias](https://mlsanity.com/paper/2110.15664/) (2021)
- [A precortical module for robust CNNs to light variations](https://mlsanity.com/paper/2202.07432/) (2022)
- [Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessment](https://mlsanity.com/paper/2412.03210/) (2024)

## Abstract (arXiv)

Robustness to variations in lighting conditions is a key objective for any deep vision system. To this end, our paper extends the receptive field of convolutional neural networks with two residual components, ubiquitous in the visual processing system of vertebrates: On-center and off-center pathways, with excitatory center and inhibitory surround; OOCS for short. The on-center pathway is excited by the presence of a light stimulus in its center but not in its surround, whereas the off-center one is excited by the absence of a light stimulus in its center but not in its surround. We design OOCS pathways via a difference of Gaussians, with their variance computed analytically from the size of the receptive fields. OOCS pathways complement each other in their response to light stimuli, ensuring this way a strong edge-detection capability, and as a result, an accurate and robust inference under challenging lighting conditions. We provide extensive empirical evidence showing that networks supplied with the OOCS edge representation gain accuracy and illumination-robustness compared to standard deep models.