用于弱监督行人重识别的对比多示例学习
Contrastive Multiple Instance Learning for Weakly Supervised Person ReID
AI总结：
本文提出CMIL框架，通过单一模型和对比损失解决弱监督行人重识别问题，在多个数据集上达到先进性能，并发布新数据集WL-MUDD。
摘要：
获取大规模、精确标注的行人重识别（ReID）数据集是一个重大挑战。弱监督ReID已开始解决这一问题，尽管其性能落后于全监督方法。为此，我们提出了对比多示例学习（CMIL），这是一种专为更有效的弱监督ReID量身定制的新框架。CMIL的独特之处在于仅需单一模型且无需伪标签，同时利用了对比损失——这项技术已显著提升了传统ReID性能，但在以往所有基于MIL的方法中均未采用。通过在三个数据集上的广泛实验与分析，CMIL不仅在SYSU-30k数据集上以更少假设达到先进水平，还在WL-market1501和Weakly Labeled MUddy racer re-iDentification dataset (WL-MUDD)数据集上持续超越所有基线。我们引入并发布WL-MUDD数据集，作为MUDD数据集的扩展，包含来自PerformancePhoto.co实际应用中的自然弱标签。所有代码和数据可在https://drive.google.com/file/d/1rjMbWB6m-apHF3Wg_cfqc8QqKgQ21AsT/view?usp=drive_link获取。
英文摘要：
The acquisition of large-scale, precisely labeled datasets for person re-identification (ReID) poses a significant challenge. Weakly supervised ReID has begun to address this issue, although its performance lags behind fully supervised methods. In response, we introduce Contrastive Multiple Instance Learning (CMIL), a novel framework tailored for more effective weakly supervised ReID. CMIL distinguishes itself by requiring only a single model and no pseudo labels while leveraging contrastive losses -- a technique that has significantly enhanced traditional ReID performance yet is absent in all prior MIL-based approaches. Through extensive experiments and analysis across three datasets, CMIL not only matches state-of-the-art performance on the large-scale SYSU-30k dataset with fewer assumptions but also consistently outperforms all baselines on the WL-market1501 and Weakly Labeled MUddy racer re-iDentification dataset (WL-MUDD) datasets. We introduce and release the WL-MUDD dataset, an extension of the MUDD dataset featuring naturally occurring weak labels from the real-world application at PerformancePhoto.co. All our code and data are accessible at https://drive.google.com/file/d/1rjMbWB6m-apHF3Wg_cfqc8QqKgQ21AsT/view?usp=drive_link.
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。
