A Comprehensive Review of Deep Reinforcement Learning for Object Detection
Zhiyao Wen, Wentao Zhang, Minfeng Qian · 2021
Object detection is one of the most fundamental and significant problems in computer vision, and has received great attention in recent years. At the same time, it is applied to various fields, such as Large image processing and Abstract-Object Detection. The aim of Object detection is detecting an instance of the visual certain class (such as humans, bikes) in digital images. Deep Reinforcement Learning (DRL), as a modern machine learning technology, has been greatly inspired by deep learning and reinforcement learning. DRL has both their advantages, excellent perception, and decision-making ability. In this work, we aim to provide a comparative review of deep reinforcement learning for object detection tasks to place different approaches in context.