Abstract
Lifelong person re-identification attempts to recognize people across cameras and integrate new knowledge from continuous data streams. Key challenges involve addressing catastrophic forgetting caused by parameter updating and domain shift, and maintaining performance in seen and unseen domains. Many previous works rely on data memories to retain prior samples. However, the amount of retained data increases linearly with the number of training domains, leading to continually increasing memory consumption. Additionally, these methods may suffer significant performance degradation when data preservation is prohibited due to privacy concerns. To address these limitations, we propose using textual descriptions as guidance to encourage the ReID model to learn cross-domain invariant features without retaining samples. The key insight is that natural language can describe pedestrian instances with an invariant style, suggesting a shared textual space for any pedestrian images. By leveraging this shared textual space as an anchor, we can prompt the ReID model to embed images from various domains into a unified semantic space, thereby alleviating catastrophic forgetting caused by domain shifts. To achieve this, we introduce a task-driven dynamic textual prompt framework in this paper. This model features a dynamic prompt fusion module, which adaptively constructs and fuses two different textual prompts as anchors. This effectively guides the ReID model to embed images into a unified semantic space. Additionally, we design a text-visual feature alignment module to learn a more precise mapping between fine-grained visual and textual features. We also developed a learnable knowledge distillation module that allows our model to dynamically balance retaining existing knowledge with acquiring new knowledge. Extensive experiments demonstrate that our method outperforms SOTAs under various settings.
Abstract (translated)
终身行人重识别旨在跨摄像头识别人员，并整合连续数据流中的新知识。关键挑战包括解决由参数更新导致的灾难性遗忘和领域转移问题，以及在已见与未见过的领域中保持性能。许多先前的工作依赖于数据记忆来保留之前的样本。然而，随着训练领域的增加，所保留的数据量线性增长，导致内存消耗持续增加。此外，由于隐私方面的顾虑禁止保存数据时，这些方法可能会遭受显著的性能下降。为了解决这些问题，我们提出使用文本描述作为指导，促使ReID模型学习跨域不变特征而不必保留样本。核心见解是自然语言可以以一种不变的方式描述行人实例，表明存在一个任何行人都共享的文本空间。通过利用这个共享的文本空间作为锚点，我们可以提示ReID模型将来自不同领域的图像嵌入到统一的语义空间中，从而缓解由领域转移导致的灾难性遗忘问题。为了实现这一目标，本文引入了一种任务驱动的动态文本提示框架。该模型具有一种动态提示融合模块，能够自适应地构建并融合两种不同的文本提示作为锚点。这有效地引导ReID模型将图像嵌入到一个统一的语义空间中。此外，我们设计了一个文本视觉特征对齐模块，以学习更精确的细粒度视觉与文本特征之间的映射关系。我们还开发了一种可学习的知识蒸馏模块，使我们的模型能够动态平衡保留已有知识和获取新知识的能力。广泛的实验表明，在各种设置下，我们的方法优于现有的最先进技术（SOTAs）。
URL
https://arxiv.org/abs/2411.06023
