Test-Time Adaptation with Query-Dependent Residuals for Visual Document Retrieval

2026-09-23

AI Summary

为解决视觉文档检索中适应性问题，提出Q-REACT方法，通过查询依赖残差和低秩转换来利用有限的重排序器反馈改进检索效果。

Abstract

Visual document retrieval (VDR) systems depend on page embeddings computed before deployment, which makes adaptation difficult when encoder parameters or corpus re-encoding are unavailable. Rerankers provide useful relevance signals, but conventional reranking applies them only to selected queries and candidate pages. We introduce Q-REACT, a query-side test-time adaptation method that converts limited reranker feedback into reusable retrieval improvements. Q-REACT learns a shared low-rank transformation that produces query-dependent residuals, combines adapted query scores with document-level context, and distills reranker preferences with a student distribution normalized over the complete task-specific page index. This design lets unscored pages compete through cached embeddings while keeping the encoders and page index fixed. Across eight ViDoRe V3 tasks and five open-weight and proprietary backbones, Q-REACT improves average retrieval over evaluated baselines at sparse and full-coverage budgets, transfers to held-out queries and tasks, and adds little inference overhead. The results show that finite reranker feedback can be amortized across a query collection without retraining or rebuilding the retriever.

Problem

• Visual Document Retrieval
• Test-Time Adaptation
• Reranker Feedback

Innovation

• Test-Time Adaptation
• Query-Dependent Residuals
• Reranker Feedback
• Low-Rank Transformation
• Visual Document Retrieval