FASHION-RQ：挖掘层级语义结构自动评估时尚检索

View PDF HTML (experimental)

Abstract:Evaluating fashion retrieval systems remains challenging due to the limited availability of benchmarks that capture the fine-grained, open-ended queries encountered in real-world search and recommendation. Existing benchmarks often rely on manual curation, predefined taxonomies, or synthetic prompts, limiting scalability and semantic coverage. We introduce FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion Retrieval, an automated framework that derives user-type queries and relevance sets directly from catalog structure. Our key insight is that hierarchical discrete representations learned by Residual Quantized Variational Autoencoders (RQ-VAE) organize products into semantically coherent clusters at progressively finer granularities. We leverage this structure to construct FASHION-RQBENCH, a scalable benchmark without manual query annotation or predefined taxonomies. We propose four complementary tasks for evaluating ranking, relevance classification, fine-grained sibling discrimination, and paraphrase robustness, alongside query- and attribute-level relevance metrics. Experiments across recent retrieval models demonstrate that FASHION-RQBENCH differentiates model capabilities across query types and attributes. A human study further shows that benchmark queries achieve comparable naturalness and higher intent clarity than real user queries, supporting their validity for real-world evaluation. The code and FASHION-RQBENCH dataset will be publicly released upon acceptance.

Subjects:	Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Cite as:	arXiv:2610.17841 [cs.IR]
	(or arXiv:2610.17841v1 [cs.IR] for this version)
	https://doi.org/10.48550/arXiv.2610.17841 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Tripti Shukla [view email]
[v1] Tue, 13 Oct 2026 06:59:54 UTC (6,072 KB)