# Gabor Layers Enhance Network Robustness

arXiv: https://arxiv.org/abs/1912.05661 · HTML: https://mlsanity.com/paper/1912.05661/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2019.

## Built on by (most cited first, 9 of 9)

- [3DGabSplat: 3D Gabor Splatting for Frequency-adaptive Radiance Field Rendering](https://mlsanity.com/paper/2508.05343/) (2025)
- [Frequency learning for structured CNN filters with Gaussian fractional derivatives](https://mlsanity.com/paper/2111.06660/) (2021)
- [FViT: A Focal Vision Transformer with Gabor Filter](https://mlsanity.com/paper/2402.11303/) (2024)
- [Frequency Dropout: Feature-Level Regularization via Randomized Filtering](https://mlsanity.com/paper/2209.09844/) (2022)
- [On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks](https://mlsanity.com/paper/2209.11740/) (2022)
- [Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning](https://mlsanity.com/paper/2401.08603/) (2023)
- [ExplainFix: Explainable Spatially Fixed Deep Networks](https://mlsanity.com/paper/2303.10408/) (2023)
- [Robustness Emerges Early in Training Dynamics, but Is Not Preserved](https://mlsanity.com/paper/2608.04442/) (2026)
- [Suppress and Diversify: Refining Robust Pathways for Corruption Robustness](https://mlsanity.com/paper/2608.06712/) (2026)

## Abstract (arXiv)

We revisit the benefits of merging classical vision concepts with deep learning models. In particular, we explore the effect on robustness against adversarial attacks of replacing the first layers of various deep architectures with Gabor layers, i.e. convolutional layers with filters that are based on learnable Gabor parameters. We observe that architectures enhanced with Gabor layers gain a consistent boost in robustness over regular models and preserve high generalizing test performance, even though these layers come at a negligible increase in the number of parameters. We then exploit the closed form expression of Gabor filters to derive an expression for a Lipschitz constant of such filters, and harness this theoretical result to develop a regularizer we use during training to further enhance network robustness. We conduct extensive experiments with various architectures (LeNet, AlexNet, VGG16 and WideResNet) on several datasets (MNIST, SVHN, CIFAR10 and CIFAR100) and demonstrate large empirical robustness gains. Furthermore, we experimentally show how our regularizer provides consistent robustness improvements.