Attributes improve person re-identification by adapting query space
In PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-Identification
Computer Vision and Pattern Recognition
Summary
Person re-identification is the task of recognizing the same person from different images or descriptions, which is hard when lighting, viewpoint, or background changes. The authors note that using attributes like clothing color can help, but directly comparing attribute matches is not reliable. They propose PRAISE, a method that adapts the search space based on the most relevant attributes for each query, improving matching without needing extra labels. This approach works for both image-to-image and text-to-image searches and shows better results in experiments.
What this means in practice
- •For video surveillance operators: Improve matching accuracy of person search systems by adapting retrieval models using query-specific visual attribute cues at inference time.
- •For digital asset managers: Enhance image search by refining the retrieval process based on query-conditioned attribute relationships without requiring new labels or retraining.
Authors
Rajarshi Bhattacharya, Aryan Shukla, Shakeeb Murtaza, Christian Desrosiers, Jose Dolz, Maguelonne Heritier, Eric Granger
Abstract
Person re-identification (ReID) ranks an image gallery using either an image query or a textual query. In image-to-image (I2I) ReID, viewpoint, illumination, occlusion, and background changes can make distractors appear more similar than the true match. In text-to-image (T2I) ReID, incomplete or ambiguous descriptions may omit key visual evidence. We study this problem for vision-language model (VLM) based ReID, where attributes such as clothing color and carried objects provide useful fine-grained matching cues. However, directly using attribute-prompt similarities as retrieval scores is unreliable because templated prompts can be biased, correlated, and poorly calibrated. We therefore propose \textbf{PR}ompt-guided \textbf{A}ttribute-based \textbf{I}nference-time \textbf{S}imilarity \textbf{E}nhancement (\texttt{PRAISE}), a query-side test-time adaptation framework for VLM-based ReID. Instead of treating prompts as scores, \texttt{PRAISE} uses a transferable attribute-prompt bank to construct an \emph{Attribute-Conditioned Subspace} (ACS): a query-dependent low-rank subspace induced by the most compatible attribute prompts. ACS provides a controlled attribute-conditioned geometry for reshaping query--gallery affinities and guiding lightweight inference-time updates without identity or attribute labels. Experiments across multiple I2I- and T2I-ReID benchmarks show that \texttt{PRAISE} consistently improves VLM retrieval backbones and outperforms both generic and ReID-specific TTA baselines.