arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.06012cs.CVcs.AI
收藏

T2I-VeRW: 基于部件级细粒度感知的文本到图像车辆检索

T2I-VeRW: Part-level Fine-grained Perception for Text-to-Image Vehicle Retrieval

School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院);School of Artificial Intelligence, Anhui University(安徽大学人工智能学院)

Xiao Wang, Ziwen Wang, Weizhe Kong, Wentao Wu, Yuehang Li, Aihua Zheng, Chenglong Li, Jin Tang

AI总结:

本文提出PFCVR模型,通过部件级局部对齐和双向掩码恢复模块实现文本到图像的车辆检索,构建了新的大规模数据集T2I-VeRW,实验结果显示PFCVR在两个基准数据集上均取得优异的检索准确率。

摘要:

车辆重识别(Re-ID)旨在从非重叠摄像头拍摄的图像中检索与给定查询最相似的图像。将车辆Re-ID扩展到基于文本的查询,使得在只有目击者描述的情况下也能进行检索。本文提出PFCVR,一种用于文本到图像车辆重识别的部件级细粒度跨模态车辆检索模型。PFCVR在部件级别构建局部配对的图像和文本,并引入可学习的部件查询标记,将部件特定和完整句子的上下文聚合后再与视觉部件特征对齐。在该显式局部对齐之上,双向掩码恢复模块让每种模态在另一种模态的指导下重建其被掩码的内容,隐式地将局部对应关系转化为全局特征对齐。此外,我们构建了一个新的大规模数据集称为T2I-VeRW,包含14,668张图像,涵盖1,796个车辆身份,具有细粒度部件级注释。在T2I-VeRI数据集上的实验结果表明,PFCVR实现了29.2%的Rank-1准确率,优于最佳竞争方法3.7个百分点。在新提出的T2I-VeRW基准上,PFCVR实现了55.2%的Rank-1准确率,优于一组最近的最先进方法。源代码将在https://github.com/Event-AHU/Neuromorphic_ReID上发布。

英文摘要:

Vehicle Re-identification (Re-ID) aims to retrieve the most similar image to a given query from images captured by non-overlapping cameras. Extending vehicle Re-ID from image-only queries to text-based queries enables retrieval in real-world scenarios where only a witness description of the target vehicle is available. In this paper, we propose PFCVR, a Part-level Fine-grained Cross-modal Vehicle Retrieval model for text-to-image vehicle re-identification. PFCVR constructs locally paired images and texts at the part level and introduces learnable part-query tokens that aggregate both part-specific and full-sentence context before aligning with visual part features. On top of this explicit local alignment, a bi-directional mask recovery module lets each modality reconstruct its masked content under the guidance of the other, implicitly bridging local correspondences into global feature alignment. Furthermore, we construct a new large-scale dataset called T2I-VeRW, which contains 14,668 images covering 1,796 vehicle identities with fine-grained part-level annotations. Experimental results on the T2I-VeRI dataset show that PFCVR achieves 29.2\% Rank-1 accuracy, improving over the best competing method by +3.7\% percentage points. On the newly proposed T2I-VeRW benchmark, PFCVR achieves 55.2\% Rank-1 accuracy, outperforming a comprehensive set of recent state-of-the-art methods. Source code will be released on https://github.com/Event-AHU/Neuromorphic_ReID

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑