From Pixels to Purchase: Building and Evaluating a Taxonomy-Decoupled Visual Search Engine for Home Goods E-commerce

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lyu, Cheng, Zhang, Jingyue, Maunu, Ryan, Li, Mengwei, DeGenova, Vinny, Pei, Yuanli
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917207400775680
author Lyu, Cheng
Zhang, Jingyue
Maunu, Ryan
Li, Mengwei
DeGenova, Vinny
Pei, Yuanli
author_facet Lyu, Cheng
Zhang, Jingyue
Maunu, Ryan
Li, Mengwei
DeGenova, Vinny
Pei, Yuanli
contents Visual search is critical for e-commerce, especially in style-driven domains where user intent is subjective and open-ended. Existing industrial systems typically couple object detection with taxonomy-based classification and rely on catalog data for evaluation, which is prone to noise that limits robustness and scalability. We propose a taxonomy-decoupled architecture that uses classification-free region proposals and unified embeddings for similarity retrieval, enabling a more flexible and generalizable visual search. To overcome the evaluation bottleneck, we propose an LLM-as-a-Judge framework that assesses nuanced visual similarity and category relevance for query-result pairs in a zero-shot manner, removing dependence on human annotations or noise-prone catalog data. Deployed at scale on a global home goods platform, our system improves retrieval quality and yields a measurable uplift in customer engagement, while our offline evaluation metrics strongly correlate with real-world outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11769
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Pixels to Purchase: Building and Evaluating a Taxonomy-Decoupled Visual Search Engine for Home Goods E-commerce
Lyu, Cheng
Zhang, Jingyue
Maunu, Ryan
Li, Mengwei
DeGenova, Vinny
Pei, Yuanli
Computer Vision and Pattern Recognition
Visual search is critical for e-commerce, especially in style-driven domains where user intent is subjective and open-ended. Existing industrial systems typically couple object detection with taxonomy-based classification and rely on catalog data for evaluation, which is prone to noise that limits robustness and scalability. We propose a taxonomy-decoupled architecture that uses classification-free region proposals and unified embeddings for similarity retrieval, enabling a more flexible and generalizable visual search. To overcome the evaluation bottleneck, we propose an LLM-as-a-Judge framework that assesses nuanced visual similarity and category relevance for query-result pairs in a zero-shot manner, removing dependence on human annotations or noise-prone catalog data. Deployed at scale on a global home goods platform, our system improves retrieval quality and yields a measurable uplift in customer engagement, while our offline evaluation metrics strongly correlate with real-world outcomes.
title From Pixels to Purchase: Building and Evaluating a Taxonomy-Decoupled Visual Search Engine for Home Goods E-commerce
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.11769