Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation
Video-based scene graph generation (VidSGG) is an approach that aims to represent video content in a dynamic graph by identifying visual entities and their relationships. Due to the inherently biased distribution and missing annotations in the training data, current VidSGG methods have been found to perform poorly on less-represented predicates. In this paper, we propose an explicit solution to address this under-explored issue by supplementing missing predicates that should be appear in the ground-truth annotations. Dubbed Trico, our method seeks to supplement the missing predicates by exploring three complementary spatio-temporal correlations. Guided by these correlations, the missing labels can be effectively supplemented thus achieving an unbiased predicate predictions. We validate the effectiveness of Trico on the most widely used VidSGG datasets, i.e., VidVRD and VidOR. Extensive experiments demonstrate the state-of-the-art performance achieved by Trico, particularly on those tail predicates.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph GenerationMissing LabelsScene Graph GenerationVideo scene graph generationSimilar Papers 제목 키워드 기반
Rethinking the Evaluation of Unbiased Scene Graph Generation
Current Scene Graph Generation (SGG) methods tend to predict frequent predicate categories and fail to recognize rare ones due to the severe imbalanced distribution of predicates. To improve the robustness of SGG models …
DiversityGraph GenerationScene Graph GenerationTriplet+1Mutually Guided Few-shot Learning for Relational Triple Extraction
Knowledge graphs (KGs), containing many entity-relation-entity triples, provide rich information for downstream applications. Although extracting triples from unstructured texts has been widely explored, most of them req…
Cross-Domain Few-ShotDecoderFew-Shot LearningKnowledge Graphs+2Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings. However, people can grasp new knowledge by learning a few instan…
NeuronTune: Towards Self-Guided Spurious Bias Mitigation
Deep neural networks often develop spurious bias, reliance on correlations between non-essential features and classes for predictions. For example, a model may identify objects based on frequently co-occurring background…
Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation
Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-…
Unbiased Scene Graph Generation