Several approaches have been proposed in recent literature to alleviate the
long-tail problem, mainly in object classification tasks. In this paper, we
make the first large-scale study concerning the task of Long-Tail Visual
Relationship Recognition (LTVRR). LTVRR aims at improving the learning of
structured visual relationships that come from the long-tail (e.g., "rabbit
grazing on grass"). In this setup, the subject, relation, and object classes
each follow a long-tail distribution. To begin our study and make a future
benchmark for the community, we introduce two LTVRR-related benchmarks, dubbed
VG8K-LT and GQA-LT, built upon the widely used Visual Genome and GQA datasets.
We use these benchmarks to study the performance of several state-of-the-art
long-tail models on the LTVRR setup. Lastly, we propose a visiolinguistic
hubless (VilHub) loss and a Mixup augmentation technique adapted to LTVRR
setup, dubbed as RelMix. Both VilHub and RelMix can be easily integrated on top
of existing models and despite being simple, our results show that they can
remarkably improve the performance, especially on tail classes. Benchmarks,
code, and models have been made available at:
this https URL

本文是对 Long-Tail Visual Relationship Recognition（LTVRR）任务的第一次大规模研究。通过引入 VG8K-LT 和 GQA-LT 等基于 Visual Genome 和 GQA 数据集的相关基准，研究了几种使用最先进的长尾模型在 LTVRR 设置中的性能。最后，介绍了一种 VilHub 损失和一种 RelMix 增强技术，能够显著提高性能，尤其是尾部类别。