paper-with-me

Papers

Fourier Sensitivity and Regularization of Computer Vision Models

2023-01-31 · Kiran Krishnamachari, See-Kiong Ng, Chuan-Sheng Foo

Recent work has empirically shown that deep neural networks latch on to the Fourier statistics of training data and show increased sensitivity to Fourier-basis directions in the input. Understanding and modifying this Fourier-sensitivity of computer vision models may help improve their robustness. Hence, in this paper we study the frequency sensitivity characteristics of deep neural networks using a principled approach. We first propose a basis trick, proving that unitary transformations of the input-gradient of a function can be used to compute its gradient in the basis induced by the transformation. Using this result, we propose a general measure of any differentiable model's Fourier-sensitivity using the unitary Fourier-transform of its input-gradient. When applied to deep neural networks, we find that computer vision models are consistently sensitive to particular frequencies dependent on the dataset, training method and architecture. Based on this measure, we further propose a Fourier-regularization framework to modify the Fourier-sensitivities and frequency bias of models. Using our proposed regularizer-family, we demonstrate that deep neural networks obtain improved classification accuracy on robustness evaluations.

📄 PDF Abstract BibTeX arXiv:2301.13514

Code (0)

등록된 구현이 없습니다.

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks

2019-09-19 · Sekitoshi Kanai, Yasutoshi Ida, Yasuhiro Fujiwara, Masanori Yamada 외

We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, recent studies have shown that the convoluti…

Adversarial AttackAdversarial RobustnessSensitivity

Sensitivity-Constrained Fourier Neural Operators for Forward and Inverse Problems in Parametric Differential Equations

2025-05-13 · Abdolmehdi Behroozi, Chaopeng Shen and, Daniel Kifer

Parametric differential equations of the form du/dt = f(u, x, t, p) are fundamental in science and engineering. While deep learning frameworks such as the Fourier Neural Operator (FNO) can efficiently approximate solutio…

Sensitivity

On Regularizing Coordinate-MLPs

2022-02-01 · Sameera Ramasinghe, Lachlan MacDonald, Simon Lucey

We show that typical implicit regularization assumptions for deep neural networks (for regression) do not hold for coordinate-MLPs, a family of MLPs that are now ubiquitous in computer vision for representing high-freque…

regression

Scaling Up Computer Vision Neural Networks Using Fast Fourier Transform

2023-02-02 · Siddharth Agrawal

Deep Learning-based Computer Vision field has recently been trying to explore larger kernels for convolution to effectively scale up Convolutional Neural Networks. Simultaneously, new paradigm of models such as Vision Tr…

Spatial Frequency Sensitivity Regularization for Robustness

2021-09-29 · Kiran Chari, Chuan-Sheng Foo, See-Kiong Ng

The ability to generalize to out-of-distribution data is a major challenge for modern deep neural networks. Recent work has shown that deep neural networks latch on to superficial Fourier statistics of the training data …

Sensitivity