Papers › Panoptic Scene Graph Generation with Semantics-Prototype Learning

Panoptic Scene Graph Generation with Semantics-Prototype Learning

28 Jul 2023arXiv:2307.15567archive 2025-07-28

Li Li, Wei Ji, Yiming Wu, Mengze Li, You Qin, Lina Wei, Roger Zimmermann

Panoptic Scene Graph Generation (PSG) parses objects and predicts their relationships (predicate) to connect human language and visual scenes. However, different language preferences of annotators and semantic overlaps between predicates lead to biased predicate annotations in the dataset, i.e. different predicates for same object pairs. Biased predicate annotations make PSG models struggle in constructing a clear decision plane among predicates, which greatly hinders the real application of PSG models. To address the intrinsic bias above, we propose a novel framework named ADTrans to adaptively transfer biased predicate annotations to informative and unified ones. To promise consistency and accuracy during the transfer process, we propose to measure the invariance of representations in each predicate class, and learn unbiased prototypes of predicates with different intensities. Meanwhile, we continuously measure the distribution changes between each presentation and its prototype, and constantly screen potential biased data. Finally, with the unbiased predicate-prototype representation embedding space, biased annotations are easily identified. Experiments show that ADTrans significantly improves the performance of benchmark models, achieving a new state-of-the-art performance, and shows great generalization and effectiveness on multiple datasets.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lili0415/psg-biased-annotation officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph GenerationPanoptic Scene Graph GenerationScene Graph Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Scene Graph Generation PSG Dataset ADTrans R@20 26.0 #3 of 9 Archive leaderboard report
Panoptic Scene Graph Generation PSG Dataset ADTrans mR@20 26.4 #3 of 9 Archive leaderboard report
Scene Graph Generation Visual Genome ADTrans Recall@50 23.0 #12 of 19 Archive leaderboard report
Scene Graph Generation Visual Genome ADTrans mR@100 19.2 #12 of 19 Archive leaderboard report
Scene Graph Generation Visual Genome ADTrans mR@50 15.8 #12 of 19 Archive leaderboard report
Scene Graph Generation Visual Genome ADTrans mean Recall @100 19.2 #12 of 19 Archive leaderboard report
Scene Graph Generation Visual Genome ADTrans mean Recall @20 12.3 #12 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections