返回全部资讯
OpenAI 官方博客T1·基座大模型

Image GPT:Transformer 生成图像研究

原标题:Image GPT
45AI 研判分

该研究证明,与语言模型类似,在像素序列上训练的大型 Transformer 模型能够生成连贯的图像补全和样本。通过建立样本质量与图像分类准确率之间的相关性,研究发现最佳生成模型在无监督设置下具备可与顶级卷积网络相竞争的特征提取能力。

报道正文

We find that, just as a large transformer model trained on language can generate coherent text, the same exact model trained on pixel sequences can generate coherent image completions and samples. By establishing a correlation between sample quality and image classification accuracy, we show that our best generative model also contains features competitive with top convolutional nets in the unsupervised setting.