A new image classification method using CNN transfer learning and web data augmentation. (1st April 2018)

• Record Type: Journal Article
• Authors: Han, Dongmei; Liu, Qigang; Fan, Weiguo
• Is Part Of: Expert systems with applications. Volume 95(2018)
• Page Start: 43
• Page End: 56
• Publication Date: 2018-04-01
• Subjects: Feature transferring -- Data augmentation -- Convolutional neural network -- Feature representation -- Parameter fine-tuning -- Bayesian optimization; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2017.11.028
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: We do image classification on training data limited dataset with deep learning. Transfer learning is employed to overcome the serious over-fitting. Web data augmentation is developed to improve the classification performance. Bayesian optimization is employed to facilitate the hyper-parameter search. Abstract: Since Convolutional Neural Network (CNN) won the image classification competition 202 (ILSVRC12), a lot of attention has been paid to deep layer CNN study. The success of CNN is attributed to its superior multi-scale high-level image representations as opposed to hand-engineering low-level features. However, estimating millions of parameters of a deep CNN requires a large number of annotated samples, which currently prevents many superior deep CNNs (such as AlexNet, VGG, ResNet) being applied to problems with limited training data. To address this problem, a novel two-phase method combining CNN transfer learning and web data augmentation is proposed. With our method, the useful feature presentation of pre-trained network can be efficiently transferred to target task, and the original dataset can be augmented with the most valuable Internet images for classification. Our method not only greatly reduces the requirement of a large training data, but also effectively expand the training dataset. Both of method features contribute to the considerable over-fitting reduction of deep CNNs on small dataset. In addition, we successfully apply Bayesian optimization to solve the tuff problem, hyper-parameter tuning, in network fine-tuning. Our solution is applied to six public small datasets. Extensive experiments show that, comparing to traditional methods, our solution can assist the popular deep CNNs to achieve better performance. Particularly, ResNet can outperform all the state-of-the-art models on six small datasets. The experiment results prove that the proposed solution will be the great tool for dealing with practice problems which are related to use deep CNNs on small dataset.