MoMo: 一种用于文本、图像和多模态表示的共享编码器模型（英文版）

英文标题：MoMo: A shared encoder Model for text, image and multi-Modal representations中文摘要：本文提出了一种自主监督的共享编码器模型，在数据、内存和运行时效率高的同时，在几个视觉、语言和多模式基准测试中取得了强大结果。英文摘要：We propose a self-supervised shared encoder model that achieves strongresults on several visual, language and multimodal benchmarks while being data,memory and run-time efficient. We make three key contributions. First, incontrast to most existing works, we use a single transformer with all theencoder layers processing both the text and the ima