paper-with-me

FashionCLIP

2000년 도입 · 논문 2편에서 사용

FashionCLIP is a fine-tuned CLIP model on fashion data (more than 800K pairs). It is the first foundation model for Fashion.

출처: Contrastive language and vision learning of general fashion concepts

소개 논문: Contrastive language and vision learning of general fashion concepts

Vision and Language Pre-Trained Models · Computer Vision