TY - GEN
T1 - Balanced mini-batch training for imbalanced image data classification with neural network
AU - Shimizu, Ryota
AU - Asako, Kosuke
AU - Ojima, Hiroki
AU - Morinaga, Shohei
AU - Hamada, Mototsugu
AU - Kuroda, Tadahiro
N1 - Funding Information:
ACKNOWLEDGMENT This work is supported by JST ACCEL Grant Number JPMJAC1502, Japan. The egg images we used were kindly provided by Shikoku Instrumentation Co. Ltd.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - We propose a novel method of training neural networks for industrial image classification that can reduce the effect of imbalanced data in supervised training. We considered visual quality inspection of industrial products as an image-classification task and attempted to solve this with a convolutional neural network; however, a problem of imbalanced data emerged in supervised training in which the neural network cannot optimize parameters. Since most industrial products are not defective, samples of defective products were fewer than those of the non-defective products; this difference in the number of samples causes an imbalance in training data. A neural network trained with imbalanced data often has varied levels of precision in determining each class depending on the difference in the number of class samples in the training data, which is a significant problem in industrial quality inspection. As a solution to this problem, we propose a balanced mini-batch training method that can virtually balance the class ratio of training samples. In an experiment, the neural network trained with the proposed method achieved higher classification ability than that trained with over-sampled or undersampled data for two types of imbalanced image datasets.
AB - We propose a novel method of training neural networks for industrial image classification that can reduce the effect of imbalanced data in supervised training. We considered visual quality inspection of industrial products as an image-classification task and attempted to solve this with a convolutional neural network; however, a problem of imbalanced data emerged in supervised training in which the neural network cannot optimize parameters. Since most industrial products are not defective, samples of defective products were fewer than those of the non-defective products; this difference in the number of samples causes an imbalance in training data. A neural network trained with imbalanced data often has varied levels of precision in determining each class depending on the difference in the number of class samples in the training data, which is a significant problem in industrial quality inspection. As a solution to this problem, we propose a balanced mini-batch training method that can virtually balance the class ratio of training samples. In an experiment, the neural network trained with the proposed method achieved higher classification ability than that trained with over-sampled or undersampled data for two types of imbalanced image datasets.
KW - convolutional neural network
KW - image classification
KW - imbalanced data
KW - mini-batch training
KW - visual quality inspection
UR - http://www.scopus.com/inward/record.url?scp=85064228342&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064228342&partnerID=8YFLogxK
U2 - 10.1109/AI4I.2018.8665709
DO - 10.1109/AI4I.2018.8665709
M3 - Conference contribution
AN - SCOPUS:85064228342
T3 - Proceedings - 2018 1st IEEE International Conference on Artificial Intelligence for Industries, AI4I 2018
SP - 27
EP - 30
BT - Proceedings - 2018 1st IEEE International Conference on Artificial Intelligence for Industries, AI4I 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1st IEEE International Conference on Artificial Intelligence for Industries, AI4I 2018
Y2 - 26 September 2018 through 28 September 2018
ER -