Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the model to be pre-trained and use self-attention to learn image-text semantic alignments in a brute force manner, in this paper, we propose a new learning method Oscar (Object-Semantics Aligned Pre-training), which uses object tags detected in images as anchor points to significantly ease the learning of alignments. Our method is motivated by the observation that the salient objects in an image can be accurately detected, and are often mentioned in the paired text. We pre-train an Oscar model on the public corpus of 6.5 million text-image pairs, and fine-tune it to downstream tasks, creating new state-of-the-arts on six well-established vision-language understanding and generation tasks.

本文介绍了一种基于目标检测的图像-文本预训练学习方法Oscar，通过使用在图像中检测到的目标标签作为锚点，显著简化模型中的图像与文本的语义对齐，使其在六个视觉-语言理解和生成任务中创造了新的最好成果。

Oscar: 面向视觉语言任务的对象-语义对齐预训练模型