Abstract
We propose unsupervised multi-scenario (UMS) person re-identification (ReID) as a new task that expands ReID across diverse scenarios (cross-resolution, clothing change, etc.) within a single coherent framework. To tackle UMS-ReID, we introduce image-text knowledge modeling (ITKM) -- a three-stage framework that effectively exploits the representational power of vision-language models. We start with a pre-trained CLIP model with an image encoder and a text encoder. In Stage I, we introduce a scenario embedding in the image encoder and fine-tune the encoder to adaptively leverage knowledge from multiple scenarios. In Stage II, we optimize a set of learned text embeddings to associate with pseudo-labels from Stage I and introduce a multi-scenario separation loss to increase the divergence between inter-scenario text representations. In Stage III, we first introduce cluster-level and instance-level heterogeneous matching modules to obtain reliable heterogeneous positive pairs (e.g., a visible image and an infrared image of the same person) within each scenario. Next, we propose a dynamic text representation update strategy to maintain consistency between text and image supervision signals. Experimental results across multiple scenarios demonstrate the superiority and generalizability of ITKM; it not only outperforms existing scenario-specific methods but also enhances overall performance by integrating knowledge from multiple scenarios.
Abstract (translated)
我们提出了一种新的任务——无监督多场景（UMS）人员重新识别（ReID），该任务旨在通过单一连贯框架扩展ReID在各种场景中的应用，如跨分辨率和着装变化等。为了解决UMS-ReID问题，我们引入了图像文本知识建模（ITKM）——一个三阶段框架，有效地利用了视觉-语言模型的表征能力。 首先，从预训练的CLIP模型开始，该模型包含一个图像编码器和一个文本编码器。在第一阶段，我们在图像编码器中引入场景嵌入，并微调编码器以适应性地利用来自多个场景的知识。第二阶段，我们优化了一组学习到的文本嵌入与第一阶段生成的伪标签相关联，并提出了一个多场景分离损失函数，以便增加跨场景文本表示之间的差异。 在第三阶段，首先引入了群级别和实例级别的异构匹配模块，在每个场景中获取可靠的异构正样本对（例如，同一人的可见图像和红外图像）。接下来，我们提出了一种动态文本表征更新策略，以保持文本和图像监督信号之间的一致性。跨多个场景的实验结果表明，ITKM具有优越性和泛化能力；它不仅超越了现有的特定场景方法，并且通过整合来自多场景的知识提升了整体性能。
URL
https://arxiv.org/abs/2601.11243
