Efficient Conditional Pre-training for Transfer Learning

Shuvam Chakraborty
Shuvam Chakraborty
Kumar Ayush
Kumar Ayush
Kumar Tanmay
Kumar Tanmay
Evan Sheehan
Evan Sheehan
Cited by: 0|Bibtex|Views6
Other Links: arxiv.org

Abstract:

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) Pre-training on a large scale dataset and (2) finetuning on the target dataset. This strategy helps reduce the dependency on the target dataset and improves convergence rate and generalization on the target task. Although pre-training on large s...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments