Problem
Research questions and friction points this paper is trying to address.
Multimodal product models
attribute completion
visual support
risk control
e-commerce search
CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search
🤖 AI Summary
本文提出CVE-SAI方法，通过视觉证据指导选择性属性索引，解决电商搜索中属性预测不准确及缺乏风险控制的问题。
📝 Abstract
Multimodal product models can complete missing e-commerce attributes, yet current methods still optimize attribute-answer accuracy without verifying visual support, conflate transient prediction with persistent index admission, and lack explicit risk control over factually incorrect or visually unsupported values. We address these gaps with Counterfactual Visual Evidence-Guided Selective Attribute Indexing (CVE-SAI), which first infers and freezes an ontology-constrained candidate from the primary image and attribute question without catalog text, and then decides whether that candidate should enter the index. Focus-Zone Distortion (FZD) constructs an attribute-specific visual-dependence proxy through a controlled counterfactual intervention, and Evidence-Guided Attention Redistribution (EGAR) uses the proxy to refine ontology-constrained scoring. The canonical candidate is frozen before evidence necessity, evidence retention, nuisance-transformation stability, and candidate-specific catalog-text conflict audits; catalog text can only tighten admission and cannot revise the candidate. Independent family-level calibration selects one policy with a simultaneous one-sided finite-sample bound under a 5% unsafe-admission budget. Experiments on five visual attributes derived from Amazon Berkeley Objects show that CVE-SAI improves attribute inference and evidence localization, achieves the highest certified admission coverage under the shared risk protocol, and yields the strongest controlled retrieval performance with the lowest unsafe auto-induced exposure among automatic-admission systems. Separating inference from admission therefore enables visually supported attribute completion to improve retrieval while limiting persistent index contamination.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Counterfactual Visual Evidence-Guided
Selective Attribute Indexing
Focus-Zone Distortion
Evidence-Guided Attention Redistribution
🔎 Similar Papers
No similar papers found.
