多尺度目标检测的深度学习研究综述

目标检测一直以来都是计算机视觉领域的研究热点之一，其任务是返回给定图像中的单个或多个特定目标的类别与矩形包围框坐标.随着神经网络研究的飞速进展，R-CNN检测器的诞生标志着目标检测正式进入深度学习时代，速度和精度相较于传统算法均有了极大的提升.但是，目标检测的尺度问题对于深度学习算法而言也始终是一个难题，即检测器对于尺度极大或极小的目标的检测精度会显著下降，因此近年来有不少学者在研究如何才能更好地实现多尺度目标检测.过往虽然已经出现了一系列的综述文章从算法流程、网络结构、训练方式和数据集等方面对基于深度学习的目标检测算法进行了总结与分析，但是对多尺度目标检测的归纳和整理却鲜有人涉足.因此，本文首先对基于深度学习的目标检测的两个主要算法流派的奠基过程进行了回顾，包括以R-CNN系列为代表的两阶段算法和以YOLO、SSD为代表的一阶段算法;然后，以多尺度目标检测的实现为核心，重点讲解了图像金字塔、构建网络内的特征金字塔等典型策略;最后，对多尺度目标检测的现状进行总结，并针对未来的研究方向进行展望.

Deep Learning for Multi-scale Object Detection: A Survey

Object detection is a classic computer vision task which aims to detect multiple objects of certain classes within a given image by bounding-box-level localization. With the rapid development of neural network technology and the birth of R-CNN detector as a milestone, a series of deep-learning-based object detectors have been developed in recent years, showing the overwhelming speed and accuracy advantage against traditional algorithms. However, how to precisely detect objects in large scale variance, also known as the scale problem, still remains a great challenge even for the deep learning methods, while many scholars have made several contributions to it over the last few years. Although there are already dozens of surveys focusing on the summarization of deep-learning-based object detectors in several aspects including algorithm procedure, network structure, training and datasets, very few of them concentrate on the methods of multi-scale object detection. Therefore, in this paper, we firstly review the foundation of the deep-learning-based detectors in two main streams, including the two-stage detectors like R-CNN and one-stage detectors like YOLO and SSD. Then, we discuss the effective approaches to address the scale problems including most commonly used image pyramids, in-network feature pyramids, etc. At last, we conclude the current situations of the multi-scale object detection and look ahead at the future research directions.