On the Impact of Data Set Size in Transfer Learning Using Deep Neural Networks

By Deepak Soekhoe, P. V. D. Putten, Aske Plaat. 2016

133 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Paul S. Babyn
2. Ekta Walia
3. Sergey I. Nikolenko

In Computer Vision and Pattern Recognition

1. Paul S. Babyn
2. Ekta Walia
3. Sergey I. Nikolenko

Citations in the corpus

• ScaleNet: An Unsupervised Representation Learning Method for Limited Information (2023, neutral): “Since the same dataset is trained, there is no need to freeze the weights of the conv. layers [44].”
• Thyroid Nodule Classification in Ultrasound Images by Fine-Tuning Deep Convolutional Neural Network (2017, background): “Prior studies on the impact of database size in transfer learning using DCNN indicated that a suitable size of database for transfer learning could range from 500 to 1000 samples per class [23]; therefore, we augmented the image data to have enough number of training samples.”