arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.06794cs.CV
收藏

使用先验偏差的阻力训练:朝向无偏场景图生成

Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation

JD Explore Academy(京东探索研究院)

Chao Chen, Yibing Zhan, Baosheng Yu, Liu Liu, Yong Luo, Bo Du

摘要:

场景图生成(SGG)旨在使用对象和成对关系构建场景的结构化表示,这有利于下游任务。然而,由于训练数据的长尾分布,目前的SGG方法通常遭受次优场景图生成。为了解决这个问题,我们提出了阻力训练使用先验偏差(RTPB)的场景图生成。具体来说,RTPB使用基于分布的先验偏差来提高模型在训练过程中对不太频繁的关系的检测能力,从而提高模型在尾部类别上的泛化能力。此外,为了进一步探索对象和关系的上下文信息,我们设计了一个上下文编码骨干网络,称为双Transformer(DTrans)。我们进行了广泛的实验上一个非常流行的基准,VG150,证明我们的方法的有效性,无偏场景图生成。具体来说,我们的RTPB实现了超过10%的平均召回下,适用于目前的SGG方法的改进。此外,DTrans与RTPB的性能几乎优于所有最先进的方法,具有很大的优势。

英文摘要:

Scene Graph Generation (SGG) aims to build a structured representation of a scene using objects and pairwise relationships, which benefits downstream tasks. However, current SGG methods usually suffer from sub-optimal scene graph generation because of the long-tailed distribution of training data. To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation. Specifically, RTPB uses a distributed-based prior bias to improve models' detecting ability on less frequent relationships during training, thus improving the model generalizability on tail categories. In addition, to further explore the contextual information of objects and relationships, we design a contextual encoding backbone network, termed as Dual Transformer (DTrans). We perform extensive experiments on a very popular benchmark, VG150, to demonstrate the effectiveness of our method for the unbiased scene graph generation. In specific, our RTPB achieves an improvement of over 10% under the mean recall when applied to current SGG methods. Furthermore, DTrans with RTPB outperforms nearly all state-of-the-art methods with a large margin.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑