An experimental comparison of the widely used pre-trained deep neural networks for image classification tasks towards revealing the promise of transfer-learning.
Abdullah Talha KabakusPakize ErdogmusPublished in: Concurr. Comput. Pract. Exp. (2022)
Keyphrases
- pre trained
- transfer learning
- neural network
- training data
- knowledge transfer
- single image
- cross domain
- input image
- image classification
- image segmentation
- training examples
- reinforcement learning
- high resolution
- text categorization
- semi supervised learning
- labeled data
- machine learning algorithms
- feature points
- learning process