Improving fine-tuning of self-supervised models with Contrastive Initialization
- 23 December 2022
- journal article
- research article
- Published by Elsevier in Neural Networks
- Vol. 159, 198-207
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62072186)
- Basic and Applied Basic Research Foundation of Guangdong Province (2019B15 15130001)
This publication has 23 references indexed in Scilit:
- Data Clustering2022
- Towards effective deep transfer via attentive feature alignmentNeural Networks, 2021
- Shortcut learning in deep neural networksNature Machine Intelligence, 2020
- Learning explicitly transferable representations for domain adaptationNeural Networks, 2020
- How Useful Is Self-Supervised Pretraining for Visual Tasks?2020
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- ClusterFit: Improving Generalization of Visual Representations2020
- Deep visual domain adaptation: A surveyNeurocomputing, 2018
- Describing Textures in the Wild2014
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002