不依赖分类体系的视觉搜索，提升家居电商搜图效果。
From Pixels to Purchase: Building and Evaluating a Taxonomy-Decoupled Visual Search Engine for Home Goods E-commerce
- 用无分类区域提议和统一嵌入做相似性检索，解耦分类与搜索。
- 零样本评估框架让模型自动判断图片相似度与品类相关性。
- 线上部署后用户参与度明显提升，评测指标与真实表现高度一致。
视觉搜索在电商中至关重要，尤其在风格导向的领域，用户意图主观且开放。现有工业系统通常将目标检测与基于分类体系的分类耦合，并依赖商品目录数据进行评估，易受噪声影响，限制了鲁棒性与可扩展性。本文提出一种解耦分类体系的架构，采用无分类的区域提议与统一嵌入进行相似性检索，实现更灵活、泛化性更强的视觉搜索。为突破评估瓶颈，提出基于大模型的判官框架（LLM-as-a-Judge），以零样本方式评估查询-结果对的视觉相似性与类别相关性，摆脱对人工标注或噪声敏感的商品目录数据的依赖。该系统已在全球家居电商平台规模化部署，显著提升了检索质量，并带来可观的用户参与度增长；离线评估指标与真实业务表现高度相关。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。