- Title
- Enhanced transfer learning with ImageNet trained classification layer
- Creator
- Shermin, Tasfia; Teng, Shyh Wei; Murshed, Manzur; Lu, Guojun; Sohel, Ferdous; Paul, Manoranjan
- Date
- 2019
- Type
- Text; Book chapter
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/180891
- Identifier
- vital:15838
- Identifier
-
https://doi.org/10.1007/978-3-030-34879-3_12
- Identifier
- ISBN:978-3-030-34879-3
- Abstract
- Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of improving task performance. However, the impact of the ImageNet pre-trained classification layer in parameter fine-tuning is mostly unexplored in the literature. In this paper, we propose a fine-tuning approach with the pre-trained classification layer. We employ layer-wise fine-tuning to determine which layers should be frozen for optimal performance. Our empirical analysis demonstrates that the proposed fine-tuning performs better than traditional fine-tuning. This finding indicates that the pre-trained classification layer holds less category-specific or more global information than believed earlier. Thus, we hypothesize that the presence of this layer is crucial for growing network depth to adapt better to a new task. Our study manifests that careful normalization and scaling are essential for creating harmony between the pre-trained and new layers for target domain adaptation. We evaluate the proposed depth augmented networks for fine-tuning on several challenging benchmark datasets and show that they can achieve higher classification accuracy than contemporary transfer learning approaches.
- Publisher
- Springer
- Relation
- Image and Video Technology Chapter 12 p. 142-1455
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright Springer
- Subject
- Computer Science - Computer Vision and Pattern Recognition
- Reviewed
- Hits: 907
- Visitors: 828
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|