ReLIC-SGG: Relation Lattice Completion for Open-Vocabulary Scene Graph Generation
Amir Hosseini, Sara Farahani, Xinyi Li, Suiyang Guang

TL;DR
ReLIC-SGG is a novel framework for open-vocabulary scene graph generation that models relation incompleteness and semantic relations to improve predicate recognition and recover missing relations.
Contribution
It introduces a relation lattice and positive-unlabeled learning to handle incomplete annotations and semantic variability in open-vocabulary SGG.
Findings
Improves recognition of rare and unseen predicates.
Recovers missing relations more effectively.
Outperforms existing methods on multiple benchmarks.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
