Look in the Middle: Structural Anchor Pruning for Scalable Visual RAG Indexing
This provides a scalable solution for Visual RAG systems, addressing a domain-specific bottleneck in visual document retrieval.
The paper tackles the problem of high index vector size overheads in Vision-Language Models for Visual Document Retrieval by proposing Structural Anchor Pruning (SAP), a training-free method that reduces index vectors by over 90% while maintaining robust retrieval fidelity on the ViDoRe benchmark.
Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive index vector size overheads. Training-free pruning solutions (e.g., EOS-attention based methods) can reduce index vector size by approximately 60% without model adaptation, but often underperform random selection in high-compression scenarios (> 80%). Prior research (e.g., Light-ColPali) attributes this to the conclusion that visual token importance is inherently query-dependent, thereby questioning the feasibility of training-free pruning. In this work, we propose Structural Anchor Pruning (SAP), a training-free pruning method that identifies key visual patches from middle layers to achieve high performance compression. We also introduce Oracle Score Retention (OSR) protocol to evaluate how layer-wise information affects compression efficiency. Evaluations on the ViDoRe benchmark demonstrate that SAP reduces index vectors by over 90% while maintaining robust retrieval fidelity, providing a highly scalable solution for Visual RAG. Furthermore, our OSR-based analysis reveals that semantic structural anchor patches persist in the middle layers, unlike traditional pruning solutions that focus on the final layer where structural signals dissipate.