Image GPT

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.

Unsupervised and self-supervised learning,¹ or learning without human-labeled data, is a longstanding challenge of machine learning. Recently, it has seen incredible success in language, as transformer² models like BERT,³ GPT-2,⁴ RoBERTa,⁵ T5,⁶ and other variants⁷⁸⁹¹⁰ have achieved top performance on a wide array of language tasks. However, the same broad class of models has not been successful in producing strong features for image classification.¹¹ Our work aims to understand and bridge this gap.

More at: https://openai.com/blog/image-gpt/