Abstract
Recent vision-language models such as CLIP provide strong cross-modal alignment, but current CLIP-guided ReID pipelines rely on global features and fixed prompts. This limits their ability to capture fine-grained attribute cues and adapt to diverse appearances. We propose ALADIN, an attribute-language distillation network that distills knowledge from a frozen CLIP teacher to a lightweight ReID student. ALADIN introduces fine-grained attribute-local alignment to establish adaptive text-visual correspondence and robust representation learning. A Scene-Aware Prompt Generator produces image-specific soft prompts to facilitate adaptive alignment. Attribute-local distillation enforces consistency between textual attributes and local visual features, significantly enhancing robustness under occlusions. Furthermore, we employ cross-modal contrastive and relation distillation to preserve the inherent structural relationships among attributes. To provide precise supervision, we leverage Multimodal LLMs to generate structured attribute descriptions, which are then converted into localized attention maps via CLIP. At inference, only the student is used. Experiments on Market-1501, DukeMTMC-reID, and MSMT17 show improvements over CNN-, Transformer-, and CLIP-based methods, with better generalization and interpretability.
Abstract (translated)
近期视觉语言模型（如CLIP）展现出强大的跨模态对齐能力，但当前基于CLIP引导的行人重识别（ReID）流程仍依赖全局特征与固定提示词，这限制了其捕捉细粒度属性线索及适应多样外观的能力。我们提出ALADIN——一种属性-语言蒸馏网络，可将冻结的CLIP教师模型的知识迁移至轻量级ReID学生模型。ALADIN引入细粒度属性-局部对齐机制，以建立自适应文本-视觉对应关系并实现鲁棒的表征学习。其场景感知提示生成器可产生图像相关的软提示词，促进自适应对齐；属性局部蒸馏则强制文本属性与局部视觉特征保持一致，显著提升遮挡场景下的鲁棒性。此外，我们采用跨模态对比蒸馏与关系蒸馏，以保留属性间的固有结构关系。为提供精确监督，我们利用多模态大语言模型生成结构化属性描述，再通过CLIP将其转换为局部化注意力图。推理阶段仅需学生网络。在Market-1501、DukeMTMC-reID与MSMT17数据集上的实验表明，该方法优于基于CNN、Transformer及CLIP的现有方案，具有更优泛化性与可解释性。
URL
https://arxiv.org/abs/2603.21482
