Existing vision-language pre-training (VLP) methods primarily rely on paired image-text datasets, which are either annotated by enormous human labors, or crawled from the internet followed by elaborate data cleaning techniques. To reduce the dependency on well-aligned image-text pairs, it is promising to directly leverage the large-scale text-only and image-only corpora. This paper proposes a data augmentation method, namely cross-modal CutMix (CMC), for implicit cross-modal alignment learning in unpaired VLP. Specifically, CMC transforms natural sentences from the textual view into a multi-modal view, where visually-grounded words in a sentence are randomly replaced by diverse image patches with similar semantics. There are several appealing proprieties of the proposed CMC. First, it enhances the data diversity while keeping the semantic meaning intact for tackling problems where the aligned data are scarce; Second, by attaching cross-modal noise on uni-modal data, it guides models to learn token-level interactions across modalities for better denoising. Furthermore, we present a new unpaired VLP method, dubbed as VLMixer, that integrates CMC with contrastive learning to pull together the uni-modal and multi-modal views for better instance-level alignments among different modalities. Extensive experiments on five downstream tasks show that VLMixer could surpass previous state-of-the-art unpaired VLP methods.

本文提出一种名为跨模态CutMix（CMC）的数据增强方法，用于隐式的跨模态对齐学习，在没有对齐图像文本对的情况下从纯文本和图像语料库中学习。同时，该论文还提出了一种新的无对齐图像文本预训练方法，名为VLMixer，通过将CMC与对比学习相结合，可以更好地对齐不同视图中的实例。实验结果表明，VLMixer可以超过以前的无对齐VLP方法。

通过跨模态CutMix进行非成对视觉-语言预训练的VLMixer