An Empirical study of object detection methods with deep ensemble and stochastic selection of activation functions

The task of object detection is one of the challenging problems in computer vision. Over the recent years, as deep learning has rapidly evolved, researchers have dedicated considerable efforts to experimenting and contributing to improving object detection performance and its associated tasks, including object classification, localization, and image segmentation. Generally, the performance of any object detector is evaluated through detection accuracy and inference time. The introduction of YOLO (You Only Look Once) and its architectural successors have notably improved detection accuracy. The presented approach suggested changing the backbone of Yolov4 and Yolov3 by replacing them with a custom ResNet50 convolutional neural network. The architecture of the ResNet50 is changed to design a new model by replacing each activation layer of a ResNet50 which is usually a ReLU layer with a different variants of ReLU AF stochastically drawn from a set of activation functions. The goal of this project is to evaluate the performance of modified CNN with Yolo’s base CNN network and to evaluate the performance of ensemble methods.