paper-with-me

홈 › Papers

Exploring Frequency Domain Interpretation of Convolutional Neural Networks

2019-11-27 · Zhongfan Jia, Chenglong Bao, Kaisheng Ma

Many existing interpretation methods of convolutional neural networks (CNNs) mainly analyze in spatial domain, yet model interpretability in frequency domain has been rarely studied. To the best of our knowledge, there is no study on the interpretation of modern CNNs from the perspective of the frequency proportion of filters. In this work, we analyze the frequency properties of filters in the first layer as it is the entrance of information and relatively more convenient for analysis. By controlling the proportion of different frequency filters in the training stage, the network classification accuracy and model robustness is evaluated and our results reveal that it has a great impact on the robustness to common corruptions. Moreover, a learnable modulation of frequency proportion with perturbation in power spectrum is proposed from the perspective of frequency domain. Experiments on CIFAR-10-C show 10.97% average robustness gains for ResNet-18 with negligible natural accuracy degradation.

📄 PDF Abstract BibTeX arXiv:1911.12044

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Similar Papers 제목 키워드 기반

Evaluating Adversarial Robustness in the Spatial Frequency Domain

2024-05-10 · Keng-Hsin Liao, Chin-Yuan Yeh, Hsi-Wen Chen, Ming-Syan Chen

Convolutional Neural Networks (CNNs) have dominated the majority of computer vision tasks. However, CNNs' vulnerability to adversarial attacks has raised concerns about deploying these models to safety-critical applicati…

Adversarial Robustness

Frequency Matters: Explaining Biases of Face Recognition in the Frequency Domain

2025-01-28 · Marco Huber, Fadi Boutros, Naser Damer

Face recognition (FR) models are vulnerable to performance variations across demographic groups. The causes for these performance differences are unclear due to the highly complex deep learning-based structure of face re…

Face Recognition

Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspective

2022-08-20 · Gihyun Kim, Juyeop Kim, Jong-Seok Lee

The Vision Transformer has emerged as a powerful tool for image classification tasks, surpassing the performance of convolutional neural networks (CNNs). Recently, many researchers have attempted to understand the robust…

Adversarial Robustnessimage-classificationImage Classification

Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs

2025-06-15 · Lu Chen, Han Yang, Hu Wang, Yuxin Cao 외

Adversarial examples have attracted significant attention over the years, yet understanding their frequency-based characteristics remains insufficient. In this paper, we investigate the intriguing properties of adversari…

Adversarial Robustnessimage-classificationImage Classification

Cross-Modality High-Frequency Transformer for MR Image Super-Resolution

2022-03-29 · Chaowei Fang, Dingwen Zhang, Liang Wang, Yulun Zhang 외

Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis. Higher resolution helps to capture more detailed content, but typically induces to lower…

Image Super-ResolutionSuper-ResolutionVocal Bursts Intensity Prediction