https://arxiv.org/abs/2111.11432
Florence: A New Foundation Model for Computer Vision (Lu Yuan, Dongdong Chen, Yi-Ling Chen, Noel Codella, Xiyang Dai, Jianfeng Gao, Houdong Hu, Xuedong Huang, Boxin Li, Chunyuan Li, Ce Liu, Mengchen Liu, Zicheng Liu, Yumao Lu, Yu Shi, Lijuan Wang, Jianfeng Wang, Bin Xiao, Zhen Xiao, Jianwei Yang, Michael Zeng, Luowei Zhou, Pengchuan Zhang)
vision-language contrastive pretraining 이후 downstream task에 transfer. 온갖 벤치마크에서 sota를 찍었네요.
#pretraining #vision-language #transfer