{"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/pha-patch-wise-high-frequency-augmentation","title":"PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification","arxiv_id":null,"date":"2023-01-01","proceeding":"CVPR 2023 1","authors":["Guiwei Zhang","Yongfei Zhang","Tianyu Zhang","Bo Li","ShiLiang Pu"],"abstract":"    Although recent studies empirically show that injecting Convolutional Neural Networks (CNNs) into Vision Transformers (ViTs) can improve the performance of person re-identification, the rationale behind it remains elusive. From a frequency perspective, we reveal that ViTs perform worse than CNNs in preserving key high-frequency components (e.g, clothes texture details) since high-frequency components are inevitably diluted by low-frequency ones due to the intrinsic Self-Attention within ViTs. To remedy such inadequacy of the ViT, we propose a Patch-wise High-frequency Augmentation (PHA) method with two core designs. First, to enhance the feature representation ability of high-frequency components, we split patches with high-frequency components by the Discrete Haar Wavelet Transform, then empower the ViT to take the split patches as auxiliary input. Second, to prevent high-frequency components from being diluted by low-frequency ones when taking the entire sequence as input during network optimization, we propose a novel patch-wise contrastive loss. From the view of gradient optimization, it acts as an implicit augmentation to improve the representation ability of key high-frequency components. This benefits the ViT to capture key high-frequency components to extract discriminative person representations. PHA is necessary during training and can be removed during inference, without bringing extra complexity. Extensive experiments on widely-used ReID datasets validate the effectiveness of our method.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2023/html/Zhang_PHA_Patch-Wise_High-Frequency_Augmentation_for_Transformer-Based_Person_Re-Identification_CVPR_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2023/papers/Zhang_PHA_Patch-Wise_High-Frequency_Augmentation_for_Transformer-Based_Person_Re-Identification_CVPR_2023_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":"pha-patch-wise-high-frequency-augmentation","repo_url":"https://github.com/zhangguiwei610/pha","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}