Despite training on low-resolution ImageNet without labels, | |
we find that a GPT-2 scale model learns strong image representations as measured by linear probing, fine-tuning, and | |
low-data classification. |
Despite training on low-resolution ImageNet without labels, | |
we find that a GPT-2 scale model learns strong image representations as measured by linear probing, fine-tuning, and | |
low-data classification. |