Research

Image GPT

Source: OpenAI News 17 Jun 2020

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

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.

Why It Matters

Penemuan ini menunjukkan potensi transformer untuk menjana imej dan mengekstrak ciri tanpa penyeliaan, berimpak kepada teknologi visi komputer dan alat penciptaan imej.

Keep Reading on NadiAI

Selected Related Articles