Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model compression. However, existing knowledge distillation techniques lack an in-depth investigation and analysis of VLP, and practical guidelines for VLP-oriented distillation are still not yet explored. In this paper, we present DLIP, a simple yet efficient Distilling Language-Image Pre-training framework, through which we investigate how to distill a light VLP model. Specifically, we dissect the model distillation from multiple dimensions, such as the architecture characteristics of different modules and the information transfer of different modalities. We conduct comprehensive experiments and provide insights on distilling a light but performant VLP model. Experimental results reveal that DLIP can achieve a state-of-the-art accuracy/efficiency trade-off across diverse cross-modal tasks, e.g., image-text retrieval, image captioning and visual question answering. For example, DLIP compresses BLIP by 1.9x, from 213M to 108M parameters, while achieving comparable or better performance. Furthermore, DLIP succeeds in retaining more than 95% of the performance with 22.4% parameters and 24.8% FLOPs compared to the teacher model and accelerates inference speed by 2.7x.

通过 DLIP（一个简单有效的Distilling Language-Image Pre-training框架）这篇论文，我们从不同维度对模型蒸馏进行了深入研究和分析，包括不同模块的架构特征和不同模态的信息传递，旨在研究如何蒸馏一个轻量的VLP模型，并通过实验证明了DLIP在各种跨模态任务上取得了最先进的准确性/效率平衡，如图像-文本检索、图像描述和视觉问答等。

DLIP：语言-图像预训练的提炼