Reproduce “In PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-Identification” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Rajarshi Bhattacharya, Aryan Shukla, Shakeeb Murtaza, Christian Desrosiers, Jose Dolz, Maguelonne Heritier, Eric Granger
PRAISE adapts query representations using compatible attribute prompts to construct an orthogonal, low-rank subspace, then combines comparisons in that space with ordinary query-gallery similarity. The prompts guide comparison rather than label identities. On Market-1501 image-to-image retrieval, it reaches 46.5 mean average precision and 71.1 Rank-1, versus Norm’s 41.0 and 67.3; this benchmark result requires unlabeled gallery access and adds inference time.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.