Bi-tuning of Pre-trained Representations

no code implementations • 12 Nov 2020 • Jincheng Zhong, Ximei Wang, Zhi Kou, Jianmin Wang, Mingsheng Long

It is common within the deep learning community to first pre-train a deep neural network from a large-scale dataset and then fine-tune the pre-trained model to a specific downstream task.

Contrastive Learning Unsupervised Pre-training