An unbiased scene graph generation (SGG) algorithm referred to as Skew Class-balanced Re-weighting (SCR) is proposed for considering the unbiased predicate prediction caused by the long-tailed distribution. The prior works focus mainly on alleviating the deteriorating performances of the minority predicate predictions, showing drastic dropping recall scores, i.e., losing the majority predicate performances. It has not yet correctly analyzed the trade-off between majority and minority predicate performances in the limited SGG datasets. In this paper, to alleviate the issue, the Skew Class-balanced Re-weighting (SCR) loss function is considered for the unbiased SGG models. Leveraged by the skewness of biased predicate predictions, the SCR estimates the target predicate weight coefficient and then re-weights more to the biased predicates for better trading-off between the majority predicates and the minority ones. Extensive experiments conducted on the standard Visual Genome dataset and Open Image V4 \& V6 show the performances and generality of the SCR with the traditional SGG models.

翻译：提出了一种称为偏斜类平衡重加权（SCR）的无偏场景图生成（SGG）算法，用于解决长尾分布导致的无偏谓词预测问题。现有工作主要聚焦于缓解少数类谓词预测性能恶化（表现为召回率显著下降），却忽视了多数类谓词性能的损失。在有限SGG数据集中，多数类与少数类谓词性能之间的权衡尚未得到正确分析。为缓解该问题，本文针对无偏SGG模型引入偏斜类平衡重加权（SCR）损失函数。借助偏斜谓词预测的偏度，SCR估计目标谓词的权重系数，并对偏斜谓词进行更强加权，从而更优地平衡多数类与少数类谓词性能。在标准Visual Genome数据集及Open Image V4与V6上的大量实验表明，SCR结合传统SGG模型具有优异的性能与泛化性。