PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation

TL;DR

This paper introduces PCPL, a novel learning scheme for scene graph generation that adaptively perceives predicate correlations to address class imbalance, significantly improving tail class performance.

Contribution

The paper proposes a new Predicate-Correlation Perception Learning framework that leverages predicate correlations and a graph encoder to enhance scene graph generation.

Findings

PCPL outperforms previous methods on VG150 dataset.

Significant improvement in tail class predicate accuracy.

Maintains strong performance on head classes.

Abstract

Today, scene graph generation(SGG) task is largely limited in realistic scenarios, mainly due to the extremely long-tailed bias of predicate annotation distribution. Thus, tackling the class imbalance trouble of SGG is critical and challenging. In this paper, we first discover that when predicate labels have strong correlation with each other, prevalent re-balancing strategies(e.g., re-sampling and re-weighting) will give rise to either over-fitting the tail data(e.g., bench sitting on sidewalk rather than on), or still suffering the adverse effect from the original uneven distribution(e.g., aggregating varied parked on/standing on/sitting on into on). We argue the principal reason is that re-balancing strategies are sensitive to the frequencies of predicates yet blind to their relatedness, which may play a more important role to promote the learning of predicate features. Therefore, we propose a novel Predicate-Correlation Perception Learning(PCPL for short) scheme to adaptively seek out appropriate loss weights by directly perceiving and utilizing the correlation among predicate classes. Moreover, our PCPL framework is further equipped with a graph encoder module to better extract context features. Extensive experiments on the benchmark VG150 dataset show that the proposed PCPL performs markedly better on tail classes while well-preserving the performance on head ones, which significantly outperforms previous state-of-the-art methods.