1. Supervision exists everywhere: A data efficient contrastive language-image pretraining paradigm;li;CoRR abs/2110 05208,2021
2. SGDR: Stochastic Gra-dient Descent with Warm Restarts;loshchilov;arXiv 1608 03983 [cs math],2017
3. Microsoft coco: Common objects in context;lin;European Conference on Computer Vision,0
4. UNIMO-2: End-to-End Unified Vision-Language Grounded Learning