Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks

Several image processing tasks, such as image classification and object detection, have been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and EfficientNet, many architectures have achieved outstanding results in at least one dataset by the time of their creation. A critical factor in training concerns the network’s regularization, which prevents the structure from overfitting. This work analyzes several regularization methods developed in the past few years, showing significant improvements for different CNN models. The works are classified into three main areas: the first one is called “data augmentation,” where all the techniques focus on performing changes in the input data.…

• FD
  Fundação de Amparo à Pesquisa do Estado de São Paulo

  Awards: 2017/25908-6, 2014/12236-1, 2017/25908-6, and 2019/07665-4, 2019/, 2014/, 307066/2017-7, 2014/12236-1, 427968/2018-6, 2019/07665-4