paper-with-me

Papers

ReLIC-SGG: Relation Lattice Completion for Open-Vocabulary Scene Graph Generation

2026-04-24 · Amir Hosseini, Sara Farahani, Xinyi Li, Suiyang Guang arxiv

Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible relation phrases beyond a fixed predicate set. Existing methods usually treat annotated triplets as positives and all unannotated object-pair relations as negatives. However, scene graph annotations are inherently incomplete: many valid relations are missing, and the same interaction can be described at different granularities, e.g., \textit{on}, \textit{standing on}, \textit{resting on}, and \textit{supported by}. This issue becomes more severe in open-vocabulary SGG due to the much larger relation space. We propose \textbf{ReLIC-SGG}, a relation-incompleteness-aware framework that treats unannotated relations as latent variables rather than definite negatives. ReLIC-SGG builds a semantic relation lattice to model similarity, entailment, and contradiction among open-vocabulary predicates, and uses it to infer missing positive relations from visual-language compatibility, graph context, and semantic consistency. A positive-unlabeled graph learning objective further reduces false-negative supervision, while lattice-guided decoding produces compact and semantically consistent scene graphs. Experiments on conventional, open-vocabulary, and panoptic SGG benchmarks show that ReLIC-SGG improves rare and unseen predicate recognition and better recovers missing relations.

📄 PDF Abstract BibTeX arXiv:2604.22546

Code (0)

등록된 구현이 없습니다.

Tasks

Scene Graph GenerationGraph Learning

Similar Papers 제목 키워드 기반

The Birkhoff completion of finite lattices

2024-05-02 · Mohammad Abdulla, Johannes Hirth, Gerd Stumme

We introduce the Birkhoff completion as the smallest distributive lattice in which a given finite lattice can be embedded as semi-lattice. We discuss its relationship to implicational theories, in particular to R. Wille'…

Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?

2022-01-13 · Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Buesing 외

Despite recent progress made by self-supervised methods in representation learning with residual networks, they still underperform supervised learning on the ImageNet classification benchmark, limiting their applicabilit…

image-classificationImage ClassificationLinear evaluationRepresentation Learning+4

DALM: A Domain-Algebraic Language Model via Three-Phase Structured Generation

2026-04-17 · Chao Li arxiv

Large language models compress heterogeneous knowledge into a single parameter space, allowing facts from different domains to interfere during generation. We propose DALM, a Domain-Algebraic Language Model that replaces…

Structured Spatial Reasoning with Open Vocabulary Object Detectors

2024-10-09 · Negar Nejatishahidin, Madhukar Reddy Vongala, Jana Kosecka

Reasoning about spatial relationships between objects is essential for many real-world robotic tasks, such as fetch-and-delivery, object rearrangement, and object search. The ability to detect and disambiguate different …

ObjectObject RearrangementSpatial Reasoning

LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval

2025-10-15 · Nilesh Gupta, Wei-Cheng Chang, Ngot Bui, Cho-Jui Hsieh 외 arxiv

Search systems are increasingly used for reasoning-intensive queries, where what makes a document relevant requires understanding or reasoning over the query-document relation rather than relying on surface vocabulary or…