arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.13135cs.CVeess.IV
收藏

对比视觉语言预训练

Contrastive Visual-Linguistic Pretraining

Beijing University of Posts and Telecommunication(北京邮电大学);Rutgers University(罗格斯大学);The Chinese University of Hong Kong(香港中文大学);Chinese Academy of Sciences(中国科学院);Hasso Plattner Institute(哈索·普拉特纳研究院)

Lei Shi, Kai Shuang, Shijie Geng, Peng Su, Zhengkai Jiang, Peng Gao, Zuohui Fu, Gerard de Melo, Sen Su

摘要:

最近提出了几种多模态表示学习方法,如LXMERT和ViLBERT。由于在大规模多模态预训练期间捕获的高级语义信息,这些方法可以实现优异的性能。然而,由于ViLBERT和LXMERT采用视觉区域回归和分类损失,它们经常遭受域间隙和噪声标签问题,基于视觉特征已经在Visual Genome数据集上进行了预训练。为了克服这些问题,我们提出了无偏的对比视觉语言预训练(CVLP),它构建了一个基于对比学习的视觉自我监督损失。我们在几个下游任务上评估了CVLP,包括VQA,GQA和NLVR2,以验证对比学习在多模态表示学习上的优越性。我们的代码可在https://github.com/ArcherYunDong/CVLP-上获得。

英文摘要:

Several multi-modality representation learning approaches such as LXMERT and ViLBERT have been proposed recently. Such approaches can achieve superior performance due to the high-level semantic information captured during large-scale multimodal pretraining. However, as ViLBERT and LXMERT adopt visual region regression and classification loss, they often suffer from domain gap and noisy label problems, based on the visual features having been pretrained on the Visual Genome dataset. To overcome these issues, we propose unbiased Contrastive Visual-Linguistic Pretraining (CVLP), which constructs a visual self-supervised loss built upon contrastive learning. We evaluate CVLP on several down-stream tasks, including VQA, GQA and NLVR2 to validate the superiority of contrastive learning on multi-modality representation learning. Our code is available at: https://github.com/ArcherYunDong/CVLP-.

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。

↑