Deep Learning Techniques—R-CNN to Mask R-CNN: A Survey

Abstract

With the advances in the field of machine learning, statistics, and computer vision, the advanced deep learning techniques have attracted increasing research interests over the last decade. This is because of their inherent capabilities of overcoming the drawback of traditional techniques. The main contribution of this work is to provide a comprehensive description of region-based convolutional neural network (R-CNN) and its recent improvement like fast R-CNN, faster R-CNN, region-based fully convolutional networks, single shot detector, deconvolutional single shot detector, R-CNN minus R, you only look once (YOLO), mask R-CNN, etc., with brief details. This survey paper presents an overview of the last update in this field and their practical applications and its classification for ease of understanding. The performances and challenges of these techniques in terms of speed, accuracy, or simplicity are also compared. In general, the speed performance of YOLO is approximately 21 ~ 155 fps which is the fastest and the average precision of Mask R-CNN is ~47.3 which outperforms all other techniques.