Meta-Characteristics Extraction from Image Datasets for Selection of Convolutional Neural Networks

• Lucas Dias Universidade Federal Rural de Pernambuco
• Péricles Miranda Universidade Federal Rural de Pernambuco
• André Nascimento Federal Rural University of Pernambuco
• Filipe Cordeiro Federal Rural University of Pernambuco
• Rafael Mello Federal Rural University of Pernambuco
• Ricardo Prudêncio Universidade Federal de Pernambuco
• Ricardo Oliveira Universidade Federal Rural de Pernambuco

DOI: https://doi.org/10.5753/eniac.2020.12113

Abstract

Convolutional Neural Networks (CNNs) is the main solution for image classification tasks in different applications. However, selecting the most suitable CNN and its parameters for a given image dataset is usually performed by trial and error, which may take much time and computational cost. This paper proposes the Dataset2Vec method and employs Meta-Learning (MtL) to select CNN architectures for image classification. Dataset2Vec adopts a deep neural network to extract features from images datasets, embedding them in a single feature vector. To evaluate the proposed solution, it was adopted to select among six CNN algorithms for 45 two-classes image datasets. The results showed that the MtL using Dataset2Vec outperformed by different baseline methods in all performance measures evaluated, indicating the proposal was able to extract representative features from datasets of images for CNN selection.

Keywords: Deep Neural Networks, Algorithm Selection, Feature Extraction

References

Achille, A., Lam, M., Tewari, R., Ravichandran, A., Maji, S., Fowlkes, C., Soatto, S., and Perona, P. (2019). Task2Vec: Task Embedding for Meta-Learning.

Aguiar, G. J., Mantovani, R. G., Mastelini, S. M., de Carvalho, A. C., Campos, G. F., and Junior, S. B. (2019). A meta-learning approach for selecting image segmentation algorithm. Pattern Recognition Letters, 128:480–487.

Bay, H., Tuytelaars, T., and Van Gool, L. (2006). Surf: Speeded up robust features. In European conference on computer vision, pages 404–417. Springer.

Chao, W.-L., Ye, H.-J., Zhan, D.-C., Campbell, M., and Weinberger, K. Q. (2020). Revisiting Meta-Learning as Supervised Learning.

Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine learning research, 7(Jan):1–30.

Fernández-Delgado, M., Cernadas, E., Barro, S., and Amorim, D. (2014). Do we Need Hundreds of Classifiers to Solve Real World Classification Problems? Journal of Machine Learning Research, 15:3133–3181.

Krizhevsky, A. and Hinton, G. (2009). Learning multiple layers of features from tiny images. Technical report, Citeseer.

Lorena, A. C., Maciel, A. I., de Miranda, P. B., Costa, I. G., and Prudêncio, R. B. (2018). Data complexity meta-features for regression problems. Machine Learning, 107(1):209–246.

Miranda, P. B., Prudêncio, R. B., De Carvalho, A. P., and Soares, C. (2014). A hybrid meta-learning architecture for multi-objective optimization of svm parameters. Neurocomputing, 143:27–43.

Olson, D. L. (2004). Comparison of weights in topsis models. Mathematical and Computer Modelling, 40(7-8):721–727.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2011). Scikit-learn: Machine learning in python. Journal of machine learning research, 12(Oct):2825–2830.

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1–9.

Takemoto, S. and Yokota, H. (2009). Algorithm selection for intracellular image segmentation based on region similarity. In 2009 Ninth International Conference on Intelligent Systems Design and Applications, pages 1413–1418. IEEE.

Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., and Le, Q. V. (2019). Mnasnet: Platform-aware neural architecture search for mobile. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2820–2828.

Wang, S., Sun, L., Fan, W., Sun, J., Naoi, S., Shirahata, K., Fukagai, T., Tomita, Y., Ike, A., and Hashimoto, T. (2017). An automated cnn recommendation system for image classification tasks. In 2017 IEEE International Conference on Multimedia and Expo (ICME), pages 283–288. IEEE.

Yong, X., Feng, D., Rongchun, Z., and Petrou, M. (2005). Learning-based algorithm selection for image segmentation. Pattern Recognition Letters, 26(8):1059–1068.

Zoph, B., Vasudevan, V., Shlens, J., and Le, Q. V. (2018). Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8697–8710.