Seonglae ChoCross Validation 과 self-attention layer를 번갈아 가며 적용해서 적은 양의 학습 데이터로부터도 효과적으로 정보를 추출
Meta Learning 구조도 그래서 넣은거
그래서 Few shot learning 에 좋은것
storage.googleapis.com
https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/tackling-multiple-tasks-with-a-single-visual-language-model/flamingo.pdf
Tackling multiple tasks with a single visual language model
We introduce Flamingo, a single visual language model (VLM) that sets a new state of the art in few-shot learning on a wide range of open-ended multimodal tasks.
https://www.deepmind.com/blog/tackling-multiple-tasks-with-a-single-visual-language-model?fbclid=IwAR0ToGRwuXzzPAKfKSbtAZ26OIDPHfoAGCoSzenyWXUfuHb_iLMjxa1Iw10
