Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness

• URL: http://arxiv.org/abs/2506.03089v1
• Date: Tue, 03 Jun 2025 17:13:51 GMT
• Title: Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
• Authors: Lucas Piper, Arlindo L. Oliveira, Tiago Marques,
• Abstract summary: Convolutional neural networks (CNNs) trained on object recognition achieve high task performance but exhibit vulnerability when compared with biological vision.<n>We introduce Early Vision Networks (EVNets), a new class of hybrid CNNs that combine the VOneBlock with a novel SubcorticalBlock.<n>EVNets exhibit stronger emergent shape bias and overperform the base CNN architecture by 8.5% on an aggregate benchmark of robustness evaluations.
• Score: 1.8434042562191815
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Convolutional neural networks (CNNs) trained on object recognition achieve high task performance but continue to exhibit vulnerability under a range of visual perturbations and out-of-domain images, when compared with biological vision. Prior work has demonstrated that coupling a standard CNN with a front-end block (VOneBlock) that mimics the primate primary visual cortex (V1) can improve overall model robustness. Expanding on this, we introduce Early Vision Networks (EVNets), a new class of hybrid CNNs that combine the VOneBlock with a novel SubcorticalBlock, whose architecture draws from computational models in neuroscience and is parameterized to maximize alignment with subcortical responses reported across multiple experimental studies. Without being optimized to do so, the assembly of the SubcorticalBlock with the VOneBlock improved V1 alignment across most standard V1 benchmarks, and better modeled extra-classical receptive field phenomena. In addition, EVNets exhibit stronger emergent shape bias and overperform the base CNN architecture by 8.5% on an aggregate benchmark of robustness evaluations, including adversarial perturbations, common corruptions, and domain shifts. Finally, we show that EVNets can be further improved when paired with a state-of-the-art data augmentation technique, surpassing the performance of the isolated data augmentation approach by 7.3% on our robustness benchmark. This result reveals complementary benefits between changes in architecture to better mimic biology and training-based machine learning approaches.

Related papers

• VCNet: Recreating High-Level Visual Cortex Principles for Robust Artificial Vision [0.0]
  We introduce Visual Cortex Network (VCNet), a novel neural network architecture based on the macro-scale organization of the primate visual cortex.<n> VCNet emulates key biological mechanisms, including hierarchical processing across distinct cortical areas, dual-stream information segregation, and top-down predictive feedback.<n>Our results show that VCNet achieves a classification accuracy of 92.1% on Spots-10 and 74.4% on the light field dataset, surpassing contemporary models of comparable size.
  arXiv  Detail & Related papers  (2025-08-05T01:52:42Z)
• Enhanced Convolutional Neural Networks for Improved Image Classification [0.40964539027092917]
  CIFAR-10 is a widely used benchmark to evaluate the performance of classification models on small-scale, multi-class datasets.<n>We propose an enhanced CNN architecture that integrates deeper convolutional blocks, batch normalization, and dropout regularization to achieve superior performance.
  arXiv  Detail & Related papers  (2025-02-02T04:32:25Z)
• Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness [1.8434042562191815]
  CNNs struggle to classify images corrupted with common corruptions. Recent work has shown that incorporating a CNN front-end block that simulates some features of the primate primary visual cortex (V1) can improve overall model robustness. We introduce two novel biologically-inspired CNN model families that incorporate a new front-end block designed to simulate pre-cortical visual processing.
  arXiv  Detail & Related papers  (2024-09-25T11:43:29Z)
• Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis [93.0013343535411]
  We propose a novel type of analysis called Multi-Scale Class Representational Response Similarity Analysis (ClassRepSim) We show that adding STAC modules to ResNet style architectures can result in up to a 1.6% increase in top-1 accuracy. Results from ClassRepSim analysis can be used to select an effective parameterization of the STAC module resulting in competitive performance.
  arXiv  Detail & Related papers  (2023-06-16T18:29:26Z)
• Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance [1.52292571922932]
  We present a new approach to receptive field analysis that can yield these types of theoretical and empirical performance gains. Our approach is able to improve ImageNet1K performance across a wide range of well-known, state-of-the-art (SOTA) model classes.
  arXiv  Detail & Related papers  (2022-11-26T05:27:44Z)
• A Generic Shared Attention Mechanism for Various Backbone Neural Networks [53.36677373145012]
  Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
  arXiv  Detail & Related papers  (2022-10-27T13:24:08Z)
• Deeper Insights into ViTs Robustness towards Common Corruptions [82.79764218627558]
  We investigate how CNN-like architectural designs and CNN-based data augmentation strategies impact on ViTs' robustness towards common corruptions. We demonstrate that overlapping patch embedding and convolutional Feed-Forward Network (FFN) boost performance on robustness. We also introduce a novel conditional method enabling input-varied augmentations from two angles.
  arXiv  Detail & Related papers  (2022-04-26T08:22:34Z)
• A precortical module for robust CNNs to light variations [0.0]
  We present a simple mathematical model for the mammalian low visual pathway, taking into account its key elements: retina, lateral geniculate nucleus (LGN), primary visual cortex (V1) The analogies between the cortical level of the visual system and the structure of popular CNNs, used in image classification tasks, suggest the introduction of an additional preliminary convolutional module inspired to precortical neuronal circuits to improve robustness with respect to global light intensity and contrast variations in the input images. We validate our hypothesis on the popular databases MNIST, FashionMNIST and SVHN, obtaining significantly more robust CNNs with respect to these variations,
  arXiv  Detail & Related papers  (2022-02-15T14:18:40Z)
• Neural Architecture Dilation for Adversarial Robustness [56.18555072877193]
  A shortcoming of convolutional neural networks is that they are vulnerable to adversarial attacks. This paper aims to improve the adversarial robustness of the backbone CNNs that have a satisfactory accuracy. Under a minimal computational overhead, a dilation architecture is expected to be friendly with the standard performance of the backbone CNN.
  arXiv  Detail & Related papers  (2021-08-16T03:58:00Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• Neural Networks with Recurrent Generative Feedback [61.90658210112138]
  We instantiate this design on convolutional neural networks (CNNs) In the experiments, CNN-F shows considerably improved adversarial robustness over conventional feedforward CNNs on standard benchmarks.
  arXiv  Detail & Related papers  (2020-07-17T19:32:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.