Papers
arxiv:2609.04255

SAGE: Semantic Attribute Graphs for Multi-Entity Visual Retrieval

Published on Sep 1
Authors:
,
,
,
,
,
,
,

Abstract

SAGE, a training-free entity-graph retrieval framework, mitigates semantic dilution in dense document images and outperforms patch-level and OCR-based baselines on the DEAR benchmark for multi-entity visual comparison.

Dense document images often contain many fine-grained visual and textual entities whose relevance depends on a user query. Standard vision-language retrievers encode cropped regions with a single vector, which can mix distinct entity signals and obscure the evidence needed for fine-grained retrieval. We call this failure mode Semantic Dilution and quantitatively show that it degrades entity-level retrieval as a function of entity density. To mitigate it, we propose SAGE, a training-free framework that parses semantic entities from dense document images, represents them as hierarchical graph nodes with multi-vector embeddings, and retrieves query-relevant evidence through iterative entity-level subgraph matching. We also introduce DEAR, a dataset of 1,055 query--image pairs sourced from product detail pages, where each query requires retrieving and comparing multiple fine-grained entities from visually dense inputs across four question types of increasing complexity. Experiments show that SAGE substantially reduces semantic dilution and outperforms patch-level and OCR-based retrieval baselines on DEAR, achieving a Recall@3 of 0.849 and a generation score of 2.746 on multi-entity visual comparison queries. Our code is available at https://github.com/All4Nothing/SAGE.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2609.04255
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2609.04255 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.04255 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.