Abstract
Hard samples pose a significant challenge in person re-identification (ReID) tasks, particularly in clothing-changing person Re-ID (CC-ReID). Their inherent ambiguity or similarity, coupled with the lack of explicit definitions, makes them a fundamental bottleneck. These issues not only limit the design of targeted learning strategies but also diminish the model's robustness under clothing or viewpoint changes. In this paper, we propose a novel multimodal-guided Hard Sample Generation and Learning (HSGL) framework, which is the first effort to unify textual and visual modalities to explicitly define, generate, and optimize hard samples within a unified paradigm. HSGL comprises two core components: (1) Dual-Granularity Hard Sample Generation (DGHSG), which leverages multimodal cues to synthesize semantically consistent samples, including both coarse- and fine-grained hard positives and negatives for effectively increasing the hardness and diversity of the training data. (2) Hard Sample Adaptive Learning (HSAL), which introduces a hardness-aware optimization strategy that adjusts feature distances based on textual semantic labels, encouraging the separation of hard positives and drawing hard negatives closer in the embedding space to enhance the model's discriminative capability and robustness to hard samples. Extensive experiments on multiple CC-ReID benchmarks demonstrate the effectiveness of our approach and highlight the potential of multimodal-guided hard sample generation and learning for robust CC-ReID. Notably, HSAL significantly accelerates the convergence of the targeted learning procedure and achieves state-of-the-art performance on both PRCC and LTCC datasets. The code is available at this https URL.
Abstract (translated)
难例在人员再识别（ReID）任务中，特别是在换衣人员再识别（CC-ReID）中提出了重大挑战。它们内在的模棱两可或相似性，加上缺乏明确定义，构成了一个根本性的瓶颈。这些问题不仅限制了针对性学习策略的设计，也削弱了模型在衣物变化或视角变换情况下的鲁棒性。 在这篇论文中，我们提出了一种新颖的多模态引导难例生成和学习（HSGL）框架，这是首次尝试统一文本和视觉模态以明确定义、生成并优化难例的方法，并在此统一流程中进行。HSGL包含两个核心组件： 1. **双粒度难例生成**（DGHSG），利用多模态线索来合成语义一致的样本，包括粗略级和细粒度正负难例，有效增强了训练数据的难度和多样性。 2. **难例自适应学习**（HSAL），引入了一种基于困难感知的优化策略，根据文本语义标签调整特征距离，鼓励在嵌入空间中将难正例分离并拉近难负面，以增强模型对难例的判别能力和鲁棒性。 通过多个CC-ReID基准数据集上的广泛实验，证明了我们方法的有效性和多模态引导难例生成与学习对于稳健的CC-ReID具有潜在价值。特别地，HSAL显著加速了针对性学习过程的收敛，并在PRCC和LTCC数据集中达到了最先进的性能。代码可在提供的网址上获取。
URL
https://arxiv.org/abs/2507.11119
