Impact of Class Imbalance on Convolutional Neural Network Training in Multi-class Problems

Image classification is the process of assigning an image one or multiple tags that describe its content. To perform the classification, a model must be designed for learning the labels to be assigned to a given image. The assignment is made through a learning process that uses a set of previously labeled training images, which must be large enough to guarantee efficient training. Many approaches have been researched to find optimal solutions to classification problems, however, databases with large amounts of images and the increased processing power of GPUs have made convolutional neural networks (CNNs) the best choice, as they outperform traditional algorithms. This paper presents a systematic analysis aimed at understanding how the issue of class inequality affects the efficiency of a convolutionary neural network trained for a task of image classification, and presents a technique for correcting the overtraining and that the network generalization.

[1]  Shanlin Yang,et al.  Smart connected electronic gastroscope system for gastric cancer screening using multi-column convolutional neural networks , 2019, Int. J. Prod. Res..

[2]  Jun Du,et al.  Writer adaptive feature extraction based on convolutional neural networks for online handwritten Chinese character recognition , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[3]  Kyung-Ah Sohn,et al.  Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets , 2017, 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[4]  Xin Xu,et al.  Traffic Sign Recognition Using Deep Convolutional Networks and Extreme Learning Machine , 2015, IScIDE.

[5]  Atsuto Maki,et al.  A systematic study of the class imbalance problem in convolutional neural networks , 2017, Neural Networks.

[6]  Jesús Silva,et al.  Neural networks for tea leaf classification , 2020 .

[7]  Shifeng Zhang,et al.  Single-Shot Refinement Neural Network for Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Radu Tudor Ionescu,et al.  Convolutional Neural Networks for User Identification Based on Motion Sensors Represented as Images , 2020, IEEE Access.

[9]  L. Santiago,et al.  Implementation of MOPROSOFT level I and II in software development companies in the colombian caribbean, a commitment to the software product quality region , 2014, 2014 IEEE Central America and Panama Convention (CONCAPAN XXXIV).

[10]  Mohammed Bennamoun,et al.  Cost-Sensitive Learning of Deep Feature Representations From Imbalanced Data , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Mark D. McDonnell,et al.  Enhanced image classification with a fast-learning shallow convolutional neural network , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[12]  Afef Abdelkrim,et al.  Convolutional neural networks for image classification , 2018, 2018 International Conference on Advanced Systems and Electric Technologies (IC_ASET).

[13]  Omar Bonerge Pineda,et al.  Method for the Recovery of Images in Databases of Rice Grains from Visual Content , 2020, ANT/EDI40.

[14]  Lianwen Jin,et al.  High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[15]  Sébastien Ourselin,et al.  Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networks , 2017, BrainLes@MICCAI.

[16]  Neha Sharma,et al.  An Analysis Of Convolutional Neural Networks For Image Classification , 2018 .

[17]  U. Rajendra Acharya,et al.  Convolutional neural networks for multi-class brain disease detection using MRI images , 2019, Comput. Medical Imaging Graph..

[18]  I. Jeena Jacob,et al.  CAPSULE NETWORK BASED BIOMETRIC RECOGNITION SYSTEM , 2019 .

[19]  Amelec Viloria,et al.  Integration of Data Mining Techniques to PostgreSQL Database Manager System , 2019, Procedia Computer Science.

[20]  Amelec Viloria,et al.  Improvements for Determining the Number of Clusters in k-Means for Innovation Databases in SMEs , 2019, ANT/EDI40.

[21]  Shaogang Gong,et al.  Single-Label Multi-Class Image Classification by Deep Logistic Regression , 2018, AAAI.

[22]  Natarajan Sriraam,et al.  EEG based multi-class seizure type classification using convolutional neural network and transfer learning , 2020, Neural Networks.

[23]  Shenghua Gao,et al.  Single-Image Crowd Counting via Multi-Column Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Alexandr A. Kalinin,et al.  Medical Image Segmentation Using Deep Neural Networks with Pre-trained Encoders , 2020 .

[25]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Amir Asif,et al.  Siamese Neural Networks for EEG-based Brain-computer Interfaces , 2020, 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).