Through The Prism: Importance-aware Scene Graphs For Image Retrieval

Abstract

Accurately retrieving images that are semantically similar remains a fundamental challenge in computer vision, as traditional methods often fail to capture the relational and contextual nuances of a scene. We introduce PRISm (Pruning-based Image Retrieval via Importance Prediction on Semantic Graphs), a multimodal framework that advances image-to-image retrieval through two novel components. First, the Importance Prediction Module identifies and retains the most critical objects and relational triplets within an image while pruning irrelevant elements. Second, the Edge-Aware Graph Neural Network explicitly encodes relational structure and integrates global visual features to produce semantically informed image embeddings. PRISm achieves image retrieval that closely aligns with human perception by explicitly modeling the semantic importance of objects and their interactions, capabilities largely absent in prior approaches. Its architecture effectively combines relational reasoning with

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygeorgoulopoulos2025through

Related papers

• SCENIR: Visual Semantic Clarity Through Unsupervised Scene Graph Retrieval (2025)0.00
• PRISM: Product Retrieval In Shopping Carts Using Hybrid Matching (2025)0.00
• Image-to-image Retrieval By Learning Similarity Between Scene Graphs (2020)12.02
• Back To The Drawing Board: Rethinking Scene-level Sketch-based Image Retrieval (2025)0.00
• Interpreting Context Of Images Using Scene Graphs (2019)0.00
• Multi-spectral Remote Sensing Image Retrieval Using Geospatial Foundation Models (2024)9.27
• Multi-modal Retrieval Using Graph Neural Networks (2020)0.00
• Bridging The Gap Between Local Semantic Concepts And Bag Of Visual Words For Natural Scene Image Retrieval (2022)2.26