GPIC:1亿对图文数据集的视觉生成基准发布

I’m very excited by this new benchmark dataset for visual generation that is suitable for the modern...

精选理由

做视觉生成模型的研究者终于有了一个大规模、开放许可的标准化基准,可以直接用来训练和评估模型,省去自己收集和清洗数据的麻烦。

AI 摘要

斯坦福大学教授李飞飞团队推出GPIC(Giant Permissive Image Corpus),这是一个专为大规模生成模型设计的视觉生成基准数据集。该数据集包含1亿对VLM标注的图文训练对和100万对基准测试对,总计约28万亿像素。所有数据均完全开放用于研究和商业用途,并集中托管。GPIC旨在解决现有数据集在规模、许可和标注质量上的不足,为视觉生成领域提供标准化评估平台。

原文 · Fei-Fei Li

I’m very excited by this new benchmark dataset for visual generation that is suitable for the modern...

I’m very excited by this new benchmark dataset for visual generation that is suitable for the modern era of large scale generative models!🤩 Keshigeyan Chandrasegaran @keshigeyan 1/ Introducing GPIC: a Giant Permissive Image Corpus and benchmark for visual generation! 🚀100M VLM-captioned image-text pairs for training 📊1M image-text pairs for benchmarking 🖼️~28 trillion pixels 🤗Centrally Hosted ✅Fully permissive for research + commercial use Dataset, benchmark and models🧵👇 Co-led with @KyleSargentAI 🔗 View Quoted Tweet 💬 1 🔄 1 ❤️ 12 👀 778 📊 2 ⚡