COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training

CoRR(2024)

引用 0|浏览46
暂无评分
摘要
In the evolution of Vision-Language Pre-training, shifting from short-text comprehension to encompassing extended textual contexts is pivotal. Recent autoregressive vision-language models like , leveraging the long-context capability of Large Language Models, have excelled in few-shot text generation tasks but face challenges in alignment tasks. Addressing this gap, we introduce the contrastive loss into text generation models, presenting the COntrastive-Streamlined MultimOdal framework (), strategically partitioning the language model into dedicated unimodal text processing and adept multimodal data handling components. , our unified framework, merges unimodal and multimodal elements, enhancing model performance for tasks involving textual and visual data while notably reducing learnable parameters. However, these models demand extensive long-text datasets, yet the availability of high-quality long-text video datasets remains limited. To bridge this gap, this work introduces , an inaugural interleaved video-text dataset featuring comprehensive captions, marking a significant step forward. Demonstrating its impact, we illustrate how enhances model performance in image-text tasks. With 34 72% of the available data, our model demonstrates significant superiority over OpenFlamingo . For instance, in the 4-shot flickr captioning task, performance notably improves from 57.2 and are underscored by notable performance gains across 14 diverse downstream datasets encompassing both image-text and video-text tasks.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要