arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.13682cs.CVcs.CLcs.LG
收藏

VIVO:小说对象字幕的视觉词汇预训练

VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning

Microsoft Corporation(微软公司)

Xiaowei Hu, Xi Yin, Kevin Lin, Lijuan Wang, Lei Zhang, Jianfeng Gao, Zicheng Liu

摘要:

生成能够描述在字幕标记的训练数据中不可见的新对象的图像字幕是非常期望但又具有挑战性的,这是在新对象字幕挑战(nocaps)中评估的能力。在此挑战中,除了COCO Captions之外,不允许用于模型训练的其他图像标题训练数据。因此,传统的视觉语言预训练(VLP)方法不能被应用。本文介绍了可视化语音预训练(VIVO),在没有字幕注释的情况下执行预训练。通过打破VLP中成对图像-标题训练数据的依赖性,VIVO可以利用大量成对图像-标签数据来学习视觉词汇。这是通过预训练多层Transformer模型来完成的,该模型学习将图像级标签与其对应的图像区域特征对齐。为了解决图像标签的无序性,VIVO使用匈牙利匹配损失和掩码标签预测来进行预训练。我们通过微调用于图像描述的预训练模型来验证VIVO的有效性。此外,我们执行的视觉文本对齐推断我们的模型的分析。结果表明,我们的模型不仅可以生成流畅的图像字幕,描述新的对象,但也确定这些对象的位置。我们的单一模型在nocaps上取得了新的最先进的结果,并超过了人类的CIDEr评分。

英文摘要:

It is highly desirable yet challenging to generate image captions that can describe novel objects which are unseen in caption-labeled training data, a capability that is evaluated in the novel object captioning challenge (nocaps). In this challenge, no additional image-caption training data, other thanCOCO Captions, is allowed for model training. Thus, conventional Vision-Language Pre-training (VLP) methods cannot be applied. This paper presents VIsual VOcabulary pretraining (VIVO) that performs pre-training in the absence of caption annotations. By breaking the dependency of paired image-caption training data in VLP, VIVO can leverage large amounts of paired image-tag data to learn a visual vocabulary. This is done by pre-training a multi-layer Transformer model that learns to align image-level tags with their corresponding image region features. To address the unordered nature of image tags, VIVO uses a Hungarian matching loss with masked tag prediction to conduct pre-training. We validate the effectiveness of VIVO by fine-tuning the pre-trained model for image captioning. In addition, we perform an analysis of the visual-text alignment inferred by our model. The results show that our model can not only generate fluent image captions that describe novel objects, but also identify the locations of these objects. Our single model has achieved new state-of-the-art results on nocaps and surpassed the human CIDEr score.

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。

↑