{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/high-frequency-component-helps-explain-the","title":"High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks","arxiv_id":null,"date":"2020-06-01","proceeding":"CVPR 2020 6","authors":["Haohan Wang"," Xindi Wu"," Zeyi Huang"," Eric P. Xing"],"abstract":"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.\r","url_abs":"http://openaccess.thecvf.com/content_CVPR_2020/html/Wang_High-Frequency_Component_Helps_Explain_the_Generalization_of_Convolutional_Neural_Networks_CVPR_2020_paper.html","url_pdf":"http://openaccess.thecvf.com/content_CVPR_2020/papers/Wang_High-Frequency_Component_Helps_Explain_the_Generalization_of_Convolutional_Neural_Networks_CVPR_2020_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"high-frequency-component-helps-explain-the","repo_url":"https://github.com/HaohanWang/HFC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}