cs.CVMay 15, 2026

Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations

Authors: Sheikh Tanvir AhmedMd. Tanvir Raihan

Organizations: Department of Computer Science and Engineering United International University · Department of Computer Science and Engineering2026 United International University

Abstract

Understanding how objects relate to each other in space is fundamental to scene understanding, yet most contrastive pre-training approaches only model pairwise relationships, leaving richer compositional and multi-hop interactions largely unexplored. We introduce Multi-Hop Relational Contrastive Learning (MRCL), a framework that extends spatial contrastive learning to graph-structured scene representations. By tracing k-hop paths through scene graphs built from detected objects, MRCL captures implicit spatial dependencies that go well beyond what direct object pairs can express. We define a multi-level contrastive objective spanning nodes, edges, and multi-hop paths, encouraging embeddings that remain stable across object semantics while staying responsive to spatial layout. On a GQA subset, MRCL produces spatially-aware representations that improve content-based graph retrieval (NDCG@5 = 0.748) and consistently benefit downstream tasks, including spatial relationship recognition and graph-based question answering. Together, these results suggest that multi-hop relational supervision offers substantially richer structural guidance than pairwise-only methods, leading to visual representations that are more robust, compositional, and geometry-aware.

Explore similar work

CardsList
  1. HSG: Hyperbolic Scene Graph

    Apr 19, 2026Liyang Wang, Zeyu Zhang, Hao TangHyperbolic Learning3D Scene Graphs