Bibliography:

  1. Image GPT (iGPT): 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

  2. https://openai.com/index/clip

  3. ImageNet Large Scale Visual Recognition Challenge

  4. Vision Transformer: An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale

  5. https://github.com/OliverRensu/D-iGPT