InterPartAbility: 基于文本引导的部分匹配用于可解释的人员重识别
InterPartAbility: Phrase-Region Grounding for Interpretable Text-to-Image Person Re-Identification
AI总结：
本文提出InterPartAbility，通过显式部分匹配和短语-区域绑定提升TI-ReID的可解释性，引入PPIM模块实现概念级指导，生成 grounded 解释图谱，实验表明在CUHK-PEDES等基准上达到SOTA可解释性性能。
摘要：
文本到图像人员重识别（TI-ReID）依赖自然语言文本描述从大量图像库中检索最匹配的个体。尽管最近的大型视觉-语言模型（VLMs）在检索性能上表现优异，但其决策仍大多不可解释。现有的TI-ReID可解释性方法仅依赖slot-attention突出关注区域，但无法可靠地将视觉区域与语义有意义的概念绑定，限制了解释仅限于有限词汇的定性可视化。本文引入InterPartAbility，一种可解释的TI-ReID方法，通过显式部分匹配和短语-区域绑定。提出一个新的开放词汇、轻量级监督、补丁-短语交互模块（PPIM），用于训练标准TI-ReID模型，以概念级指导。基于概念的部分短语提供证据，促使模型关注相应的图像区域。InterPartAbility进一步约束CLIP ViT自注意力，以产生与每个部分级短语对齐的空间集中补丁激活，生成 grounded 解释图谱。通过适应基于扰动的评估度量，引入定量可解释性协议。实验结果表明，在CUHK-PEDES和ICFG-PEDES等具有挑战性的基准上，InterPartAbility在这些度量下达到SOTA可解释性性能，同时保持竞争性的检索准确性。
英文摘要：
Text-to-image person re-identification (TI-ReID) relies on natural-language text descriptions to retrieve top matching individuals from a gallery of reference images. While recent large vision-language models (VLMs) achieve strong retrieval performance, their decisions remain largely uninterpretable. Existing interpretability approaches in TI-ReID rely solely on slot-attention to highlight attended regions, but fail to reliably bind visual regions to semantically meaningful concepts, limiting interpretation to qualitative visualizations over a restricted vocabulary. This paper introduces InterPartAbility, an interpretable TI-ReID method that performs explicit part-wise matching and enables phrase-region grounding. Unlike parameter-heavy slot-attention methods that yield only qualitative interpretability, our open-vocabulary patch-phrase interaction module (PPIM) guides a standard TI-ReID model with concept-level phrases. Concept-based part phrases provide evidence that encourages the model to attend to the corresponding local image regions. InterPartAbility further leverages CLIP ViT self-attention to produce spatially concentrated patch activations aligned with each part-level phrase, yielding grounded explanation maps. Finally, a quantitative interpretability protocol for TI-ReID is introduced that extends current perturbation-based evaluation metrics into the TI-Reid domain. This includes a counterfactual region removal that measures retrieval degradation when top-ranked explanatory regions are removed. Empirical results on three challenging benchmarks show that InterPartAbility can achieve SOTA interpretability performance under these metrics, while sustaining competitive retrieval accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
