概念12 M：推动网络规模的图像-文本预训练以识别长尾视觉概念
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts
摘要：
大规模图像描述和视觉问答数据集的可用性为最近在视觉和语言预训练方面的成功做出了重大贡献。然而，这些数据集通常是以从其原始目标任务继承的过度限制性要求（例如，图像字幕生成），这限制了所得到的数据集规模和多样性。我们通过放松概念字幕3 M（CC 3 M）[Sharma et al. 2018]中使用的数据汇集管道，进一步推动视觉和语言预训练数据的极限，并引入概念12 M（CC 12 M），这是一个包含1200万个图像-文本对的数据集，专门用于视觉和语言预训练。我们对此数据集进行了分析，并在多个下游任务上对CC 3 M进行了有效性基准测试，重点是长尾视觉识别。我们的结果清楚地说明了扩大视觉和语言任务的预训练数据的好处，正如nocaps和概念字幕基准测试的最新结果所示。
英文摘要：
The availability of large-scale image captioning and visual question answering datasets has contributed significantly to recent successes in vision-and-language pre-training. However, these datasets are often collected with overrestrictive requirements inherited from their original target tasks (e.g., image caption generation), which limit the resulting dataset scale and diversity. We take a step further in pushing the limits of vision-and-language pre-training data by relaxing the data collection pipeline used in Conceptual Captions 3M (CC3M) [Sharma et al. 2018] and introduce the Conceptual 12M (CC12M), a dataset with 12 million image-text pairs specifically meant to be used for vision-and-language pre-training. We perform an analysis of this dataset and benchmark its effectiveness against CC3M on multiple downstream tasks with an emphasis on long-tail visual recognition. Our results clearly illustrate the benefit of scaling up pre-training data for vision-and-language tasks, as indicated by the new state-of-the-art results on both the nocaps and Conceptual Captions benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
