人工知能（AI）技術の進化は、私たちの生活に大きな変化をもたらしています。その中でも、画像認識は自動運転、医療診断、セキュリティなど、様々な分野で応用が期待される重要な技術です。従来の画像認識AIは、深層学習（Deep Learning）と呼ばれる技術 ...

Thanks for your great project. You use a BERT encoder instead of a CLIP encoder for text. Is there any specific reason for the choice? Thanks Sign up for free to join this conversation on GitHub.

CLIP was one of the earliest vision language models that was widely adopted and paved the way for multimodal models evolution. Before CLIP, all computer vision based systems were built to classify ...