Self-Supervised Visual Representation Learning via Residual Momentum

Self-Supervised Visual Representation Learning via Residual Momentum

Self-supervised learning (SSL) has emerged as a promising approach for learning representations from unlabeled data. Momentum-based contrastive frameworks such as MoCo-v3 have shown remarkable success among the many SSL methods proposed in recent years. However, a significant gap in encoder represen...

Full description

Bibliographic Details
Main Authors: Trung Xuan Pham, Axi Niu, Kang Zhang, Tee Joshua Tian Jin, Ji Woo Hong, Chang D. Yoo
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Contrastive learning
residual momentum
representation learning
self-supervised learning
knowledge distillation
teacher-student gap
Online Access:https://ieeexplore.ieee.org/document/10287941/

Internet

https://ieeexplore.ieee.org/document/10287941/

Similar Items