用细粒度属性提升跨模态行人重识别，更准且可解释。
ALADIN:Attribute-Language Distillation Network for Person Re-Identification
- 通过局部属性对齐与自适应提示生成，增强图文对应
- 在多个数据集上超越现有方法，尤其在遮挡下表现更好
- 适合需要高精度和可解释性的行人识别场景
近期视觉-语言模型如CLIP虽具备强跨模态对齐能力，但现有基于CLIP的行人重识别（ReID）方法依赖全局特征和固定提示，难以捕捉细粒度属性线索并适应多样外观。本文提出ALADIN——一种属性-语言知识蒸馏网络，将冻结的CLIP教师模型知识蒸馏至轻量级ReID学生模型。ALADIN引入细粒度属性局部对齐机制，建立自适应文本-视觉对应关系，并促进鲁棒表征学习。场景感知提示生成器生成图像特定软提示以实现自适应对齐。属性局部蒸馏确保文本属性与局部视觉特征的一致性，显著提升遮挡下的鲁棒性。此外，采用跨模态对比与关系蒸馏，保留属性间的内在结构关系。为提供精准监督，利用多模态大模型生成结构化属性描述，并通过CLIP转换为局部注意力图。推理时仅使用学生模型。在Market-1501、DukeMTMC-reID和MSMT17上的实验表明，该方法优于基于CNN、Transformer及CLIP的方法，具有更强泛化能力与可解释性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。