paper-with-me

Papers

HSG: Hyperbolic Scene Graph

2026-04-19 · Liyang Wang, Zeyu Zhang, Hao Tang arxiv

Scene graph representations enable structured visual understanding by modeling objects and their relationships, and have been widely used for multiview and 3D scene reasoning. Existing methods such as MSG learn scene graph embeddings in Euclidean space using contrastive learning and attention based association. However, Euclidean geometry does not explicitly capture hierarchical entailment relationships between places and objects, limiting the structural consistency of learned representations. To address this, we propose Hyperbolic Scene Graph (HSG), which learns scene graph embeddings in hyperbolic space where hierarchical relationships are naturally encoded through geometric distance. Our results show that HSG improves hierarchical structure quality while maintaining strong retrieval performance. The largest gains are observed in graph level metrics: HSG achieves a PP IoU of 33.17 and the highest Graph IoU of 33.51, outperforming the best AoMSG variant (25.37) by 8.14, highlighting the effectiveness of hyperbolic representation learning for scene graph modeling. Code: https://github.com/AIGeeksGroup/HSG.

📄 PDF Abstract BibTeX arXiv:2604.17454

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningContrastive Learning

Similar Papers 제목 키워드 기반

A Hyperbolic-to-Hyperbolic Graph Convolutional Network

2021-04-14 · CVPR 2021 1 · Jindou Dai, Yuwei Wu, Zhi Gao, Yunde Jia

Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to tangent spaces to realize graph convolution on hy…

General ClassificationGraph ClassificationLink PredictionNode Classification

Hyperbolic Contrastive Learning for Visual Representations beyond Objects

2022-12-01 · CVPR 2023 1 · Songwei Ge, Shlok Mishra, Simon Kornblith, Chun-Liang Li 외

Although self-/un-supervised methods have led to rapid progress in visual representation learning, these methods generally treat objects and scenes using the same lens. In this paper, we focus on learning representations…

Contrastive Learningimage-classificationImage ClassificationObject+4

HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning

2026-06-04 · Moshiur Farazi, Sameera Ramasinghe, Mahbub Ahmed Turza, Shafin Rahman arxiv

Vision-Language Models (VLMs) struggle with compositional reasoning that requires understanding inter-object relationships. A natural remedy is to inject explicit scene graph triplets $\langle s, p, o \rangle$ from an of…

Lorentzian Graph Convolutional Networks

2021-04-15 · Yiding Zhang, Xiao Wang, Chuan Shi, Nian Liu 외

Graph convolutional networks (GCNs) have received considerable research attention recently. Most GCNs learn the node representations in Euclidean geometry, but that could have a high distortion in the case of embedding g…

A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations

2026-03-14 · Neelu Madan, Àlex Pujol, Andreas Møgelmose, Sergio Escalera 외 arxiv

Slot attention has emerged as a powerful framework for unsupervised object-centric learning, decomposing visual scenes into a small set of compact vector representations called \emph{slots}, each capturing a distinct reg…