Share Email Print

Proceedings Paper

Data augmentation based on interest points of feature
Author(s): Yao Duan; Xin Niu; Guhong Nie
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In fine-grained object recognition task, over-fitting problem often occurred due to the small number of fine-gained data for each category, especially for the CNN with deep layers and millions parameters. Therefore, we proposed a data augmentation method based on interest points of feature, which can alleviate the over-fitting problem and improve the classification accuracy effectively. The key idea of our method is finding the interest points that attract the classifier which come from the output of the CNN middle layer, locating the areas corresponding to the interest points in the original images and cutting the areas out for augmentation. All work can be done through training procedure completely. The method requires no additional training models and more other parameters. We applied the proposed data augmentation method on CUB200-2011, Stanford Dogs and Aircraft datasets and achieved excellent performance with 11.32% classification accuracy improvement. The experiment results showed that the proposed method can mitigate the problem of over-fitting in fine-grained images.

Paper Details

Date Published: 9 August 2018
PDF: 7 pages
Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108060B (9 August 2018); doi: 10.1117/12.2503212
Show Author Affiliations
Yao Duan, National Univ. of Defense Technology (China)
Xin Niu, National Univ. of Defense Technology (China)
Guhong Nie, National Univ. of Defense Technology (China)

Published in SPIE Proceedings Vol. 10806:
Tenth International Conference on Digital Image Processing (ICDIP 2018)
Xudong Jiang; Jenq-Neng Hwang, Editor(s)

© SPIE. Terms of Use
Back to Top