paper-with-me

홈 › Papers

High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

2019-05-28 · Haohan Wang, Xindi Wu, Zeyi Huang, Eric P. Xing

We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN). We first notice CNN's ability in capturing the high-frequency components of images. These high-frequency components are almost imperceptible to a human. Thus the observation leads to multiple hypotheses that are related to the generalization behaviors of CNN, including a potential explanation for adversarial examples, a discussion of CNN's trade-off between robustness and accuracy, and some evidence in understanding training heuristics.

📄 PDF Abstract BibTeX arXiv:1905.13545

Code (1)

HaohanWang/HFC 공식 구현 tf

Tasks

Adversarial AttackVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

2020-06-01 · CVPR 2020 6 · Haohan Wang, Xindi Wu, Zeyi Huang, Eric P. Xing

We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN). We first notice CNN's ability in capturing the high-frequency component…

Vocal Bursts Intensity Prediction

Equivalence between Geometric Frequency and Lagrange Derivative

2024-10-03 · Federico Milano

The paper shows the equivalence between the geometric frequency of an electric quantity, namely, voltage and current, and the Lagrange derivative of a stream-line of a fluid. The geometric frequency is a concept recently…

How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization

2026-07-08 · Xinyi Wu, Siyuan Liu, Ali Jadbabaie arxiv

Rotary Position Embeddings (RoPE) provide transformers with a fixed grid of positional frequencies, yet trained models use these frequencies highly non-uniformly. We study what determines this frequency usage and propose…

Phase Matching for Out-of-Distribution Generalization

2023-07-24 · Chengming Hu, Yeqian Du, Rui Wang, Hao Chen 외

The Fourier transform, an explicit decomposition method for visual signals, has been employed to explain the out-of-distribution generalization behaviors of Deep Neural Networks (DNNs). Previous studies indicate that the…

Contrastive LearningDomain GeneralizationOut-of-Distribution GeneralizationRepresentation Learning

DC is all you need: describing ReLU from a signal processing standpoint

2024-07-23 · Christodoulos Kechris, Jonathan Dan, Jose Miranda, David Atienza

Non-linear activation functions are crucial in Convolutional Neural Networks. However, until now they have not been well described in the frequency domain. In this work, we study the spectral behavior of ReLU, a popular …

All