Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo

Chaoning Zhang, Kang Zhang, Trung X. Pham, Axi Niu, Zhinan Qiao, Chang D. Yoo, In-So Kweon. Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. pages 14421-14430, IEEE, 2022. [doi]

Abstract

Abstract is missing.