Ensemble Predicate Decoding for Unbiased Scene Graph Generation

TL;DR

This paper introduces Ensemble Predicate Decoding (EPD), a novel approach using multiple decoders to improve unbiased scene graph generation by addressing predicate bias and enhancing discriminative ability.

Contribution

The paper proposes EPD with auxiliary decoders trained on low-frequency predicates, improving predicate discrimination and reducing bias in scene graph generation.

Findings

EPD improves predicate representation capability.

EPD achieves better unbiased predicate prediction.

EPD maintains superior performance on frequent predicates.

Abstract

Scene Graph Generation (SGG) aims to generate a comprehensive graphical representation that accurately captures the semantic information of a given scenario. However, the SGG model's performance in predicting more fine-grained predicates is hindered by a significant predicate bias. According to existing works, the long-tail distribution of predicates in training data results in the biased scene graph. However, the semantic overlap between predicate categories makes predicate prediction difficult, and there is a significant difference in the sample size of semantically similar predicates, making the predicate prediction more difficult. Therefore, higher requirements are placed on the discriminative ability of the model. In order to address this problem, this paper proposes Ensemble Predicate Decoding (EPD), which employs multiple decoders to attain unbiased scene graph generation. Two auxiliary decoders trained on lower-frequency predicates are used to improve the discriminative ability of the model. Extensive experiments are conducted on the VG, and the experiment results show that EPD enhances the model's representation capability for predicates. In addition, we find that our approach ensures a relatively superior predictive capability for more frequent predicates compared to previous unbiased SGG methods.