Back to Search
Start Over
Transferring Ensemble Representations Using Deep Convolutional Neural Networks for Small-Scale Image Classification
- Source :
- IEEE Access, Vol 7, Pp 168175-168186 (2019)
- Publication Year :
- 2019
- Publisher :
- IEEE, 2019.
-
Abstract
- The deep convolutional neural networks (DCNN) require large number of training data to avoid overfitting, which makes it unsuitable for processing small-scale image datasets. The transfer learning using DCNN (TCNN) reuses pre-trained layers to generate a mid-level image representation so that the optimization of more than millions CNN parameters can be avoided. By this way, overfitting problem in small-scale data can be alleviated. However, although now many public DCNNs have been trained and can be reused, the existing TCNNs are formed by only a single pre-trained DCNN structure and cannot make full use of multiple structures of pre-trained DCNNs. At the same time, the existing ensemble CNNs have not enough good representation ability. To address this problem, we combine the conventional ideas of ensemble CNNs and propose three ensemble TCNNs (TECNN). They are the voting method based on the combination of all TCNNs, the PickOver method by finding the optimal combination, and weighted method by finding weighted combination. Different from the existing ensemble CNNs, the proposed methods do not need to retrain the component CNNs and generate ensemble transferring representations by transferring the pre-trained mid-level parameters. The mathematical models of those three methods are also provided. Their versions of using fine-tuning are also compared in the experiments. In addition, we replace the Softmax classifier with ensemble linear classifiers in the full-connection layer. They outperform the current state of the art algorithms on Caltech ImageNet and some internet image data. All this research has released as an open source library called Transferring Image Ensemble Representations using Deep Convolutional Neural Networks (TECNN). The source codes and relevant datasets in different versions are available from: http://www.cquptshuyinxia.com/TECNN.html .
- Subjects :
- General Computer Science
Computer science
02 engineering and technology
Overfitting
01 natural sciences
Convolutional neural network
010309 optics
0103 physical sciences
0202 electrical engineering, electronic engineering, information engineering
deep CNN
General Materials Science
Training set
Contextual image classification
business.industry
General Engineering
Pattern recognition
transferring Learning
Softmax function
020201 artificial intelligence & image processing
Convolutional neural networks
transferring CNN
Artificial intelligence
lcsh:Electrical engineering. Electronics. Nuclear engineering
business
Transfer of learning
Classifier (UML)
lcsh:TK1-9971
Subjects
Details
- Language :
- English
- ISSN :
- 21693536
- Volume :
- 7
- Database :
- OpenAIRE
- Journal :
- IEEE Access
- Accession number :
- edsair.doi.dedup.....37b6e5a3c2c675cc35a741261d36db14