.@OpenAI ImageGPT is one of the first transformer architectures applied to computer vision scenarios.👇 
In language, unsupervised learning algorithms that rely on word prediction (like GPT-2 and BERT) are extremely successful.
One possible reason for this success is that instances of downstream language tasks appear naturally in the text.
2/4
One possible reason for this success is that instances of downstream language tasks appear naturally in the text.
2/4
In contrast, sequences of pixels do not clearly contain labels for the images they belong to.
However, OpenAI believes that sufficiently large transformer models:
- could be applied to 2D image analysis
- learn strong representations of a dataset
3/4
However, OpenAI believes that sufficiently large transformer models:
- could be applied to 2D image analysis
- learn strong representations of a dataset
3/4
Find more about ImageGPT here: openai.com/blog/image-gpt/
Thanks for learning ML and AI with us! This is a thread from Edge#117 – our series about transformers.
4/4
Thanks for learning ML and AI with us! This is a thread from Edge#117 – our series about transformers.
4/4
• • •
Missing some Tweet in this thread? You can try to
force a refresh
