Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey

Abstract

Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have demonstrated the remarkable successes of deep reinforcement learning in various domains including finance, medicine, healthcare, video games, robotics, and computer vision. In this work, we provide a detailed review of recent and state-of-the-art research advances of deep reinforcement learning in computer vision. We start with comprehending the theories of deep learning, reinforcement learning, and deep reinforcement learning. We then propose a categorization of deep reinforcement learning methodologies and discuss their advantages and limitations. In particular, we divide deep reinforcement learning into seven main categories according to their applications in computer vision, i.e. (i)landmark localization (ii) object detection; (iii) object tracking; (iv) registration on both 2D image and 3D image volumetric data (v) image segmentation; (vi) videos analysis; and (vii) other applications. Each of these categories is further analyzed with reinforcement learning techniques, network design, and performance. Moreover, we provide a comprehensive analysis of the existing publicly available datasets and examine source code availability. Finally, we present some open issues and discuss future research directions on deep reinforcement learning in computer vision

References in corpus (27)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• High-Speed Tracking with Kernelized Correlation Filters
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Attention-Based Models for Speech Recognition
• REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
• Deep Bilateral Learning for Real-Time Image Enhancement
• MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
• Learning to reinforcement learn
• Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving
• CARLA: An Open Urban Driving Simulator
• Multi-agent Reinforcement Learning in Sequential Social Dilemmas
• Visual Saliency Based on Multiscale Deep Features
• Benchmarking Model-Based Reinforcement Learning
• Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
• A Hierarchical Neural Autoencoder for Paragraphs and Documents
• Hierarchical Object Detection with Deep Reinforcement Learning
• Tree-Structured Reinforcement Learning for Sequential Object Localization
• Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video
• SRM : A Style-based Recalibration Module for Convolutional Neural Networks
• Robust Multimodal Image Registration Using Deep Recurrent Reinforcement Learning
• Experience Replay Optimization
• Multi-modal Visual Tracking: Review and Experimental Comparison
• Generic Object Detection With Dense Neural Patterns and Regionlets
• Ultrasound Video Summarization using Deep Reinforcement Learning
• Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning
• Invertible Residual Network with Regularization for Effective Medical Image Segmentation
• Offset Curves Loss for Imbalanced Problem in Medical Segmentation