Text-to-image person re-identification (TIReID) is a compelling topic in the cross-modal community, which aims to retrieve the target person based on a textual query. Although numerous TIReID methods have been proposed and achieved promising performance, they implicitly assume the training image-text pairs are correctly aligned, which is not always the case in real-world scenarios. In practice, the image-text pairs inevitably exist under-correlated or even false-correlated, a.k.a noisy correspondence (NC), due to the low quality of the images and annotation errors. To address this problem, we propose a novel Robust Dual Embedding method (RDE) that can learn robust visual-semantic associations even with NC. Specifically, RDE consists of two main components: 1) A Confident Consensus Division (CCD) module that leverages the dual-grained decisions of dual embedding modules to obtain a consensus set of clean training data, which enables the model to learn correct and reliable visual-semantic associations. 2) A Triplet-Alignment Loss (TAL) relaxes the conventional triplet-ranking loss with hardest negatives, which tends to rapidly overfit NC, to a log-exponential upper bound over all negatives, thus preventing the model from overemphasizing false image-text pairs. We conduct extensive experiments on three public benchmarks, namely CUHK-PEDES, ICFG-PEDES, and RSTPReID, to evaluate the performance and robustness of our RDE. Our method achieves state-of-the-art results both with and without synthetic noisy correspondences on all three datasets.

翻译：文本到图像行人重识别（TIReID）是跨模态领域一个引人关注的研究课题，旨在根据文本查询检索目标行人。尽管已有大量TIReID方法被提出并取得了令人瞩目的性能，但它们隐含地假设训练图像-文本对是正确对齐的，而在实际场景中这一假设往往不成立。现实中，由于图像质量低下和标注错误，图像-文本对不可避免地存在欠相关甚至虚假相关现象，即噪声对应（NC）。为解决这一问题，我们提出了一种新颖的鲁棒双重嵌入方法（RDE），该方法即使存在噪声对应也能学习鲁棒的视觉-语义关联。具体而言，RDE包含两个主要模块：1）置信共识划分（CCD）模块，通过利用双重嵌入模块的双粒度决策获取干净训练数据的共识集，从而使模型学习正确且可靠的视觉-语义关联；2）三元组对齐损失（TAL）将传统三元组排序损失中对最难负样本的依赖（该方法倾向于快速过拟合噪声对应）松弛为对所有负样本的对数指数上界，从而防止模型过度强调虚假图像-文本对。我们在三个公开基准数据集（CUHK-PEDES、ICFG-PEDES和RSTPReID）上进行了大量实验，以评估RDE的性能和鲁棒性。我们的方法在三个数据集上，无论是否使用合成噪声对应，均取得了最先进的结果。