Fusion-Based Semantic Segmentation Using Deep Learning Architecture in Case of Very Small Training Dataset

Abstract

Semantic segmentation is a pre-processing step in computer vision-based applications. It is the task of assigning a predefined class label to every pixel of an image. Several supervised and unsupervised algorithms are available to classify pixels of an image into predefined object classes. The algorithms, such as random forest and SVM are used to obtain the semantic segmentation. Recently, convolutional neural network (CNN)-based architectures have become popular for the tasks of object detection, object recognition, and segmentation. These deep architectures perform semantic segmentation with far better accuracy than the algorithms that were used earlier. CNN-based deep learning architectures require a large dataset for training. In real life, some of the applications may not have sufficient good quality samples for training of deep learning architectures e.g. medical applications. Such a requirement initiated a need to have a technique of effective training of deep learning architecture in case of a very small dataset. Class imbalance is another challenge in the process of training deep learning architecture. Due to class imbalance, the classifier overclassifies classes with large samples. In this paper, the challenge of training a deep learning architecture with a small dataset and class imbalance is addressed by novel fusion-based semantic segmentation technique which improves segmentation of minor and major classes.