Xiaonan Zhang
ABSTRACT
At present, deep learning methods represented by artificial neural networks (ANN) has been applied in the fields of image recognition, natural language processing, intelligent control, and big data analysis. However, whether deep learning is suitable for little data has always been a controversial topic. A recent algorithm called capsule network (CapsNet) that implements an approach based on activity vectors may overcome some of the limitations of the current state of the convolution neural network (CNN) classifiers. In this study, we explore capsule networks with dynamic routing for the problem of small scale datasets. A series of experiments are conducted with capsule networks and convolution networks. Experimental results demonstrate the effectiveness of capsule networks on little data. Furthermore, when training data does not use augmentation techniques, CapsNet significantly outperform CNN, indicating that CapsNet has better generalization ability which is a very important advantage if the amount of data is relatively small.
- Schmidhuber, Jürgen. "Deep learning in neural networks: An overview." Neural networks 61 (2015): 85--117. Google Scholar
Digital Library
- Al-Saffar, Ahmed Ali Mohammed, Hai Tao, and Mohammed Ahmed Talab. "Review of deep convolution neural network in image classification." Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET), 2017 International Conference on. IEEE, 2017.Google Scholar
- Mukhometzianov, Rinat, and Juan Carrillo. "CapsNet comparative performance evaluation for image classification." arXiv preprint arXiv:1805.11195 (2018).Google Scholar
- Goodfellow, Ian J., Jonathon Shlens, and Christian Szegedy. "Explaining and harnessing adversarial examples (2014)." arXiv preprint arXiv:1412.6572.Google Scholar
- Sabour, Sara, Nicholas Frosst, and Geoffrey E. Hinton. "Dynamic routing between capsules." Advances in Neural Information Processing Systems. 2017. Google ScholarDigital Library
- Hinton, Geoffrey E., Alex Krizhevsky, and Sida D. Wang. "Transforming auto-encoders." International Conference on Artificial Neural Networks. Springer, Berlin, Heidelberg, 2011. Google ScholarDigital Library
- Wikipedia. 2017. Capsule neural network. https://en.wikipedia.org/wiki/Capsule_neural_networkGoogle Scholar
- Mobiny, Aryan, and Hien Van Nguyen. "Fast CapsNet for Lung Cancer Screening." arXiv preprint arXiv:1806.07416 (2018).Google Scholar
- Afshar, Parnian, Arash Mohammadi, and Konstantinos N. Plataniotis. "Brain tumor type classification via capsule networks." arXiv preprint arXiv:1802.10200 (2018).Google Scholar
- Zhang, Xiaonan, Pengcheng Luo, and Xinwu Hu. "A hybrid method for classification and identification of emitter signals." Systems and Informatics (ICSAI), 2017 4th International Conference on. IEEE, 2017.Google Scholar
- Shi Zhengxin. "How to use keras CNN to do kaggle cat vs. dog image recognition", May. 17. 2017. https://blog.csdn.net/shizhengxin123/article/details/72424694Google Scholar
- Zhao, Wei, et al. "Investigating Capsule Networks with Dynamic Routing for Text Classification." arXiv preprint arXiv:1804.00538 (2018).Google Scholar
- Xi, Edgar, Selina Bing, and Yang Jin. "Capsule network performance on complex data." arXiv preprint arXiv:1712.03480 (2017).Google Scholar
- Ciresan, Dan C., et al. "Flexible, high performance convolutional neural networks for image classification." IJCAI Proceedings-International Joint Conference on Artificial Intelligence. Vol. 22. No. 1. 2011. Google ScholarDigital Library
Index Terms
- Research on Classification Performance of Small-Scale Dataset Based on Capsule Network
Recommendations
Capsule network-based classification of rotator cuff pathologies from MRI
AbstractRotator cuff lesions are very frequent events. The diagnosis of these lesions is challenging and requires experience. The goal of this study is to develop a computer aided diagnosis (CAD) system based on Capsule Network (CapsNet) to ...
WideCaps: a wide attention-based capsule network for image classification
AbstractThe capsule network is a distinct and promising segment of the neural network family that has drawn attention due to its unique ability to maintain equivariance by preserving spatial relationships among the features. The capsule network has ...
Capsule Network Versus Convolutional Neural Network in Image Classification: Comparative Analysis
Computational Science – ICCS 2021AbstractMany concepts behind Capsule Networks cannot be proved due to limited research, performed so far. In the paper, we compare the CapsNet architecture with the most common implementations of convolutional networks (CNNs) for image classification. We ...
Comments