{"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/adaptive-aspect-ratios-with-patch-mixup-vit","title":"Adaptive Aspect Ratios with Patch-Mixup-ViT-based Vehicle ReID","arxiv_id":"2411.06297","date":"2024-11-09","proceeding":null,"authors":["Mei Qiu","Lauren Ann Christopher","Stanley Chien","Lingxi Li"],"abstract":"Vision Transformers (ViTs) have shown exceptional performance in vehicle re-identification (ReID) tasks. However, non-square aspect ratios of image or video inputs can negatively impact re-identification accuracy. To address this challenge, we propose a novel, human perception driven, and general ViT-based ReID framework that fuses models trained on various aspect ratios. Our key contributions are threefold: (i) We analyze the impact of aspect ratios on performance using the VeRi-776 and VehicleID datasets, providing guidance for input settings based on the distribution of original image aspect ratios. (ii) We introduce patch-wise mixup strategy during ViT patchification (guided by spatial attention scores) and implement uneven stride for better alignment with object aspect ratios. (iii) We propose a dynamic feature fusion ReID network to enhance model robustness. Our method outperforms state-of-the-art transformer-based approaches on both datasets, with only a minimal increase in inference time per image.","url_abs":"https://arxiv.org/abs/2411.06297v1","url_pdf":"https://arxiv.org/pdf/2411.06297v1.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":"adaptive-aspect-ratios-with-patch-mixup-vit","repo_url":"https://github.com/qiumei1101/adaptive_ar_pm_transreid","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"vehicle-re-identification","task_name":"Vehicle Re-Identification"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"mixup","method_name":"Mixup"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}