摘要
小目标检测长期以来是计算机视觉中的一个难点和研究热点。在深度学习的驱动下,小目标检测已取得了重大突破,并成功应用于国防安全、智能交通和工业自动化等领域。为了进一步促进小目标检测的发展,本文对小目标检测算法进行了全面的总结,并对已有算法进行了归类、分析和比较。首先,对小目标进行了定义,并概述小目标检测所面临的挑战。然后,重点阐述从数据增强、多尺度学习、上下文学习、生成对抗学习以及无锚机制等方面来提升小目标检测性能的方法,并分析了这些方法的优缺点和关联性。之后,全面介绍小目标数据集,并在一些常用的公共数据集上对已有算法进行了性能评估。最后本文对小目标检测技术的未来发展方向进行了展望。
目标检测是计算机视觉领域中的一个重要研究方向,也是其他复杂视觉任务的基础。作为图像理解和计算机视觉的基石,目标检测是解决分割、场景理解、目标跟踪、图像描述和事件检测等更高层次视觉任务的基础。小目标检测长期以来是目标检测中的一个难点,其旨在精准检测出图像中可视化特征极少的小目标(32像素×32像素以下的目标)。在现实场景中,由于小目标是的大量存在,因此小目标检测具有广泛的应用前景,在自动驾驶、智慧医疗、缺陷检测和航拍图像分析等诸多领域发挥着重要作用。近年来,深度学习技术的快速发展为小目标检测注入了新鲜血液,使其成为研究热点。然而,相对于常规尺寸的目标,小目标通常缺乏充足的外观信息,因此难以将它们与背景或相似的目标区分开来。在深度学习的驱动下,尽管目标检测算法已取得了重大突破,但是对于小目标的检测仍然是不尽人意的。在目标检测公共数据集MS COC
目标检测作为计算机视觉的基础研究,已有许多优秀的综述发表。Zou
与以往将小目标与常规目标等同对待或只关注特定应用场景下的目标检测综述不同,本文对小目标检测这一不可或缺且极具挑战性的研究领域进行了系统且深入的分析与总结。本文不仅对小目标的定义进行了解释,也对小目标检测领域存在的挑战进行了详细地分析和总结,同时重点阐述了小目标检测优化思路,包括数据增强、多尺度学习、上下文学习、生成对抗学习以及无锚机制以及其他优化策略等。此外,本文还在常用的小目标数据集上分析对比了现有算法的检测性能。最后,对本文内容进行了简要的总结,并讨论了小目标检测未来可能的研究方向和发展趋势。
不同场景对于小目标的定义各不相同,目前尚未形成统一的标准。现有的小目标定义方式主要分为以下两类,即基于相对尺度的定义与基于绝对尺度的定义。
(1)基于相对尺度定义。即从目标与图像的相对比例这一角度考虑来对小目标进行定义。Chen
但是,这些基于相对尺度的定义存在诸多问题,如这种定义方式难以有效评估模型对不同尺度目标的检测性能。此外,这种定义方式易受到数据预处理与模型结构的影响。
(2)基于绝对尺度定义。则从目标绝对像素大小这一角度考虑来对小目标进行定义。目前最为通用的定义来自于目标检测领域的通用数据集——MS COCO数据
前文中已简要阐述小目标的主流定义,通过这些定义可以发现小目标像素占比少,存在覆盖面积小、包含信息少等基本特点。这些特点在以往综述或论文中也多有提及,但是少有对小目标检测难点进行分析与总结。接下来本文将试图对造成小目标检测难度高的原因以及其面临的挑战进行分析与总结。
无论是从基于绝对尺度还是基于相对尺度的定义,小目标相对于大/中尺度尺寸目标都存在分辨率低的问题。低分辨率的小目标可视化信息少,难以提取到具有鉴别力的特征,并且极易受到环境因素的干扰,进而导致了检测模型难以精准定位和识别小目标。
小目标由于在图像中覆盖面积小,因此其边界框的定位相对于大/中尺度尺寸目标具有更大的挑战性。在预测过程中,预测边界框框偏移一个像素点,对小目标的误差影响远高于大/中尺度目标。此外,现在基于锚框的检测器依旧占据绝大多数,在训练过程中,匹配小目标的锚框数量远低于大/中尺度目标,如

图1 小目标匹配的锚框数量相对大/中尺度的目标更少
Fig.1 Small‑size objects match with fewer anchors than large/medium objects
在目标检测领域中,现有数据集大多针对大/中尺度尺寸目标,较少关注小目标这一特别的类型。MS COCO中虽然小目标占比较高,达31.62%,但是每幅图像包含的实例过多,小目标分布并不均匀。同时,小目标不易标注,一方面来源于小目标在图像中不易被人类关注,很难标全;另一方面是小目标对于标注误差更为敏感。另外,现有的小目标数据集往往针对特定场景,例如文献[
为了定位目标在图像中的位置,现有的方法大多是预先在图像的每个位置生成一系列的锚框。在训练的过程中,通过设定固定的阈值来判断锚框属于正样本还是负样本。这种方式导致了模型训练过程中不同尺寸目标的正样本不均衡问题。当人工设定的锚框与小目标的真实边界框差异较大时,小目标的训练正样本将远远小于大/中尺度目标的正样本,这将导致训练的模型更加关注大/中尺度目标的检测,而忽略小目标的检测。如何解决锚框机制导致的小目标和大/中尺度目标样本不均衡问题也是当前面临的一大挑战。
相对于大/中尺度目标,小目标具有更大概率产生聚集现象。当小目标聚集出现时,聚集区域相邻的小目标通过多次降采样后,反应到深层特征图上将聚合成一个点,导致检测模型无法区分。当同类小目标密集出现时,预测的边界框还可能会因后处理的非极大值抑制操作将大量正确预测的边界框过滤,从而导致漏检情况。另外,聚集区域的小目标之间边界框距离过近,还将导致边界框难以回归,模型难以收敛。
数据增强是一种提升小目标检测性能的最简单和有效的方法,通过不同的数据增强策略可以扩充训练数据集的规模,丰富数据集的多样性,从而增强检测模型的鲁棒性和泛化能力。在相对早期的研究中,Yaeger
近些年来,基于深度学习的卷积神经网络在处理计算机视觉任务中获得了巨大的成功。深度学习的成功很大程度上归功于数据集的规模和质量,大规模和高质量的数据能够大幅度提升模型的泛化能力。数据增强策略在目标检测领域有着广泛应用,例如Fast R‑CN
聚焦到小目标检测领域,小目标面临着分辨率低、可提取特征少、样本数量匮乏及分布不均匀等诸多挑战,数据增强的重要性愈发显著。近些年来,出现了一些适用于小目标的数据增强方法(
数据增强这一策略虽然在一定程度上解决了小目标信息量少、缺乏外貌特征和纹理等问题,有效提高了网络的泛化能力,在最终检测性能上获得了较好的效果,但同时带来了计算成本的增加。而且在实际应用中,往往需要针对目标特性做出优化,设计不当的数据增强策略可能会引入新的噪声,损害特征提取的性能,这也给算法的设计带来了挑战。
小目标与常规目标相比可利用的像素较少,难以提取到较好的特征,而且随着网络层数的增加,小目标的特征信息与位置信息也逐渐丢失,难以被网络检测。这些特性导致小目标同时需要深层语义信息与浅层表征信息,而多尺度学习将这两种相结合,是一种提升小目标检测性能的有效策略。
早期的多尺度检测有两个思路。一种是使用不同大小的卷积核通过不同的感受野大小来获取不同尺度的信息,但这种方法计算成本很高,而且感受野的尺度范围有限,Simonyan和Zisserma

图2 多尺度学习的4种方式
Fig.2 Four ways of multi‑scale learning
目标检测中的经典网络如Fast R‑CN
针对小目标易受环境干扰问题,Bell
为节省计算资源并获得更好的特征融合效果,Lin
最近,多尺度特征融合这一方法又有了新的拓展,如Nayan
总体来说,多尺度特征融合同时考虑了浅层的表征信息和深层的语义信息,有利于小目标的特征提取,能够有效地提升小目标检测性能。然而,现有多尺度学习方法在提高检测性能的同时也增加了额外的计算量,并且在特征融合过程中难以避免干扰噪声的影响,这些问题导致了基于多尺度学习的小目标检测性能难以得到进一步提升。
在真实世界中,“目标与场景”和“目标与目标”之间通常存在一种共存关系,通过利用这种关系将有助于提升小目标的检测性能。在深度学习之前,已有研
(1)基于隐式上下文特征学习的目标检测。隐式上下文特征是指目标区域周围的背景特征或者全局的场景特征。事实上,卷积神经网络中的卷积操作在一定程度上已经考虑了目标区域周围的隐式上下文特征。为了利用目标周围的上下文特征,Li

图3 上下文在目标检测中的探索历程
Fig.3 Exploration of context in object detection
为了更加充分地利用上下文信息,一些方法尝试将全局的上下文信息融入到目标检测模型中(见
(2)基于显式上下文推理的目标检测。显示上下文推理是指利用场景中明确的上下文信息来辅助推断目标的位置或类别,例如利用场景中天空区域与目标的上下文关系来推断目标的类别。上下文关系通常指场景中目标与场景或者目标与目标之间的约束和依赖关系(见
近年来,基于上下文学习的方法得到了进一步发展。Lim
基于上下文学习的方法充分利用了图像中与目标相关的信息,能够有效提升小目标检测的性能。但是,已有方法没有考虑到场景中的上下文信息可能匮乏的问题,同时没有针对性地利用场景中易于检测的结果来辅助小目标的检测。鉴于此,未来的研究方向可以从以下两个角度出发考虑:(1)构建基于类别语义池的上下文记忆模型,通过利用历史记忆的上下文来缓解当前图像中上下文信息匮乏的问题;(2)基于图推理的小目标检测,通过图模型和目标检测模型的结合来针对性地提升小目标的检测性能。
生成对抗学习的方法旨在通过将低分辨率小目标的特征映射成与高分辨率目标等价的特征,从而达到与尺寸较大目标同等的检测性能。前文所提到的数据增强、特征融合和上下文学习等方法虽然可以有效地提升小目标检测性能,但是这些方法带来的性能增益往往受限于计算成本。针对小目标分辨率低问题,Haris
目前,一种有效的方法是通过结合生成对抗网络(Generative adversarial network, GAN
近年来,基于GAN对小目标进行超分辨率重建的研究有所发展,Bai
基于生成对抗模型的目标检测算法通过增强小目标的特征信息,可以显著提升检测性能。同时,利用生成对抗模型来超分小目标这一步骤无需任何特别的结构设计,能够轻易地将已有的生成对抗模型和检测模型相结合。但是,目前依旧面临两个无法避免的问题:(1)生成对抗网络难以训练,不易在生成器和鉴别器之间取得好的平衡;(2)生成器在训练过程中产生样本的多样性有限,训练到一定程度后对于性能的提升有限。
锚框机制在目标检测中扮演着重要的角色。许多先进的目标检测方法都是基于锚框机制而设计的,但是锚框这一设计对于小目标的检测极不友好。现有的锚框设计难以获得平衡小目标召回率与计算成本之间的矛盾,而且这种方式导致了小目标的正样本与大目标的正样本极度不均衡,使得模型更加关注于大目标的检测性能,从而忽视了小目标的检测。极端情况下,设计的锚框如果远远大于小目标,那么小目标将会出现无正样本的情况。小目标正样本的缺失,将使得算法只能学习到适用于较大目标的检测模型。此外,锚框的使用引入了大量的超参,比如锚框的数量、宽高比和大小等,使得网络难以训练,不易提升小目标的检测性能。近些年无锚机制的方法成为了研究热点,并在小目标检测上取得了较好效果。
一种摆脱锚框机制的思路是将目标检测任务转换为关键点的估计,即基于关键点的目标检测方法。基于关键点的目标检测方法主要包含两个大类:基于角点的检测和基于中心的检测。基于角点的检测器通过对从卷积特征图中学习到的角点分组来预测目标边界框。DeNe

图4 无锚机制的4种形式
Fig.4 Four ways of anchor‑free methods
为了进一步提高目标检测性能,Duan
近年来,基于关键点的目标检测方法又有了新的扩展。Yang
在小目标检测这一领域,除了前文所总结的几个大类外,还有诸多优秀的方法。针对小目标训练样本少的问题,Kisantal
近些年来,随着计算资源的增加,越来越多的网络使用级联思想来平衡目标漏检率与误检率。级联这一思想来源已
另外一种思路则是分阶段检测,通过不同层级之间的配合平衡漏检与误检之间的矛盾。Chen
优化损失函数也是一种提升小目标检测性能的有效方法。Redmon
为了权衡考虑小目标的检测精度和速度,Sun
在常规目标检测数据集上,现有研究对大/中尺寸的目标已取得了不错的成效。但是,小目标的检测仍然是不尽人意的,一方面是由小目标自身特性所导致的的,另一方面是因为常规目标检测数据集中小目标存在占比少、分布不均匀等问题。接下来本文将按照时间顺序简要介绍现有的小目标数据集(见
(1)BIRDSAI数据
(2)TinyPerson数据
(3)EuroCity Persons数据
(4)WiderPerson数据
(5)DOTA数据
(6)Nighttowls数据
(7)DeepScores数据
(8)Bosch小交通灯数据
(9)CityPersons数据
(10)Tsinghua‑Tencent 100K数据
(11)WIDER FACE数据
(12)MS COCO数据
(13)Caltech行人检测数据
(14)Penn‑Fudan行人检测与分割数据
为了便于研究人员更好地了解小目标的发展现状,本文在几个常用的小目标数据集上对现有算法的性能进行了评估。
(1)MS COCO数据集。
(2)WIDER FACE数据集。
(3)TinyPerson数据集。
(4)Tsinghua‑Tencent 100K数据集。
本文对小目标检测算法进行了详尽的回顾,并对已有的算法进行了归类分析和比较。首先,本文对小目标检测定义进行了解释,并对小目标检测面临的挑战进行了分析和总结。然后,本文重点阐述了小目标检测优化思路,包括数据增强、多尺度学习、上下文学习、生成对抗学习、无锚机制以及其他优化策略等,同时对采用统一思路来提升小目标检测性能的算法进行了性能比较和分析。最后,本文全面介绍了已有的小目标检测数据集,并在这些数据集上对现有的算法进行了性能比较和分析。尽管在大数据和深度学习的驱动下,小目标检测算法得到了快速的发展。但是,小目标的检测性能仍不能满足实际应用的需求,还有很多方面值得进一步研究:
(1)特征融合方面。现有的方法通常通过融合深度神经网络中同层的多尺度特征来提升小目标的特征表达能力。尽管这种方式一定程度提升了小目标的检测性能,但是在特征融合的过程中没有考虑到语义间隔和噪声干扰的问题。因此,如何消除特征融合中的语义间隔和噪声干扰问题是未来的一个研究方向。
(2)上下文学习方面。尽管上下文在目标检测中已经得到了充分的重视,并在众多目标检测算法中得到了充分利用。但是,场景中并不是所有上下文信息都是有价值的,无效的上下文信息将可能破坏目标区域的原始特征,如何从图像中挖掘有利于提升小目标区域特征表示的上下文信息是未来的一个研究方向。此外,现有的上下文建模方法对于不同尺度目标是同等对待,并没有针对小目标而做相应的设计。因此,如何在检测模型中利用易于检测目标来辅助小目标的检测是未来的一个重要研究方向。
(3)超分辨率重构方面。尽管已有一些方法通过生成对抗的方式来提升小目标的特征,以此获得与大目标等价的特征表示,并取得了一定的成效。但是,这一类方法研究还尚少,仍有较大的研究空间。超分辨率重构是一种最直接的、可解释的提升小目标检测性能的方法。如何将超分辨率重构中先进技术与目标检测技术深度结合是未来的一个可行研究思路。
参考文献
LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: Common objects in context[C]//Proceedings of European Conference on Computer Vision. Cham: Springer, 2014: 740‑755. [百度学术]
ZOU Z,SHI Z,GUO Y,et al.Object detection in 20 years: A survey[EB/OL].(2019‑05‑13)[2019‑05‑16].https://arxiv.org/abs/1905.05055. [百度学术]
OKSUZ K,CAM B C,KALKAN S,et al.Imbalance problems in object detection: A review[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020.DOI:10.1109/TPAMI.2020.2981890. [百度学术]
ZHAO Z Q,ZHENG P,XU S,et al.Object detection with deep learning: A review[J].IEEE Transactions on Neural Networks and Learning Systems,2019,30(11): 3212‑3232. [百度学术]
AGARWAL S,TERRAIL J O D,JURIE F.Recent advances in object detection in the age of deep convolutional neural networks[EB/OL].(2018‑09‑10)[2019‑08‑20].https://arxiv.org/abs/1809.03193. [百度学术]
CHEN G,WANG H,CHEN K,et al.A survey of the four pillars for small object detection: Multiscale representation, contextual information, super‑resolution, and region proposal[J].IEEE Transactions on Systems, Man, and Cybernetics: Systems,2020,99: 1‑18. [百度学术]
TONG K,WU Y,ZHOU F.Recent advances in small object detection based on deep learning: A review[J].Image and Vision Computing,2020,97: 103910. [百度学术]
LIU Y,SUN P,WERGELES N,et al.A survey and performance evaluation of deep learning methods for small object detection[J].Expert Systems with Applications,2021,172(4): 114602. [百度学术]
梁鸿,王庆玮,张千,等.小目标检测技术研究综述[J].计算机工程与应用,2021,57(1): 17‑28. [百度学术]
LIANG Hong,WANG Qingwei,ZHANG Qian,et al.Small object detection technology: A review[J].Computer Engineering and Applications,2021,57(1): 17‑28. [百度学术]
刘颖,刘红燕,范九伦,等.基于深度学习的小目标检测研究与应用综述[J].电子学报,2019,48(3): 590‑601. [百度学术]
LIU Ying,LIU Hongyan,FAN Jiulun,et al.A survey of research and application of small object detection based on deep learning[J].Acta Electronica Sinica,2019,48(3): 590‑601. [百度学术]
CHEN C, LIU M Y, TUZEL O, et al. R‑CNN for small object detection[C]//Proceeding of Asian Conference on Computer Vision. Cham: Springer, 2016: 214‑230. [百度学术]
TORRALBA A,FERGUS R,FREEMAN W T. 80 million tiny images: A large data set for nonparametric object and scene recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(11): 1958‑1970. [百度学术]
SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large‑scale image recognition[EB/OL].(2014‑09‑04)[2015‑04‑10]. https://arxiv.org/abs/1409.1556. [百度学术]
XIA G S, BAI X, DING J, et al. DOTA: A large‑scale dataset for object detection in aerial images[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE,2018: 3974‑3983. [百度学术]
YANG S, LUO P, LOY C C, et al. Wider face: A face detection benchmark[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE,2016: 5525‑5533. [百度学术]
ZHANG S, BENENSON R, SCHIELE B. Citypersons: A diverse dataset for pedestrian detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 3213‑3221. [百度学术]
YU X, GONG Y, JIANG N, et al. Scale match for tiny person detection[C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Los Alamitos: IEEE,2020: 1257‑1265. [百度学术]
BEHRENDT K, NOVAK L, BOTROS R. A deep learning approach to traffic lights: Detection, tracking, and classification[C]// 2017 IEEE International Conference on Robotics and Automation (ICRA). Singapore: IEEE, 2017: 1370‑1377. [百度学术]
LUKAS T, ELEZI I, SCHMIDHUBER J, et al. Deepscores-a dataset for segmentation, detection and classification of tiny objects[C]//Proceedings of 2018 24th International Conference on Pattern Recognition (ICPR). New York: IEEE, 2018: 3704‑3709. [百度学术]
YAEGER L,LYON R,WEBB B.Effective training of a neural network character classifier for word recognition[J].Advances in Neural Information Processing Systems,1996,9: 807‑816. [百度学术]
SIMARD P Y, STEINKRAUS D, PLATT J C. Best practices for convolutional neural networks applied to visual document analysis[C]//Proceedings of ICDAR. [S.l.]: IEEE, 2003, 3(2003). [百度学术]
KRIZHEVSKY A, SUTSKEVER I, HINTON G E.Imagenet classification with deep convolutional neural networks[J].Advances in Neural Information Processing Systems,2012,25: 1097‑1105. [百度学术]
WAN L, ZEILER M, ZHANG S, et al. Regularization of neural networks using dropconnect[C]//Proceedings of International Conference on Machine Learning. [S.l.]: PMLR, 2013: 1058‑1066. [百度学术]
GIRSHICK R. Fast R‑CNN[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2015: 1440‑1448. [百度学术]
CAI Z, VASCONCELOS N. Cascade R‑CNN: Delving into high quality object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 6154‑6162. [百度学术]
REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real‑time object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2016: 779‑788. [百度学术]
REDMON J, FARHADI A. YOLO9000: Better, faster, stronger[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 7263‑7271. [百度学术]
DEVRIES T,TAYLOR G W.Improved regularization of convolutional neural networks with cutout[EB/OL].(2017‑08‑15)[2017‑11‑29].https://arxiv.org/abs/1708.04552. [百度学术]
ZHANG H,CISSE M,DAUPHIN Y N,et al.Mixup: Beyond empirical risk minimization[EB/OL].(2017‑10‑25)[2018‑04‑27].https://arxiv.org/abs/1710.09412. [百度学术]
YUN S, HAN D, OH S J, et al. Cutmix: Regularization strategy to train strong classifiers with localizable features[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2019: 6023‑6032. [百度学术]
BOCHKOVSKIY A,WANG C Y,LIAO H Y M.Yolov4: Optimal speed and accuracy of object detection[EB/OL].(2020‑04‑23)[2020‑04‑23].https://arxiv.org/abs/2004.10934. [百度学术]
GONG C,WANG D,LI M,et al.KeepAugment: A simple information‑preserving data augmentation approach[EB/OL].(2020‑11‑23)[2020‑11‑23].https://arxiv.org/abs/2011.11778. [百度学术]
KISANTAL M,WOJNA Z,MURAWSKI J,et al. Augmentation for small object detection[EB/OL].(2019‑02‑19)[2019‑02‑19]. https://arxiv.org/abs/1902.07296. [百度学术]
CHEN C, ZHANG Y, LV Q, et al. RRNet: A hybrid detector for object detection in drone‑captured images[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Los Alamitos: IEEE, 2019: 100‑108. [百度学术]
CHEN Y,ZHANG P,LI Z,et al.Stitcher: Feedback‑driven data provider for object detection[EB/OL].(2020‑04‑26)[2021‑03‑14]. https://arxiv.org/abs/2004.12432. [百度学术]
ZOPH B, CUBUK E D, GHIASI G, et al. Learning data augmentation strategies for object detection[C]//Proceedings of European Conference on Computer Vision. Cham: Springer, 2020: 566‑583. [百度学术]
YU F,KOLTUN V.Multi‑scale context aggregation by dilated convolutions[EB/OL].(2015‑11‑23)[2016‑04‑30].https://arxiv.org/abs/1511.07122. [百度学术]
DAI J, QI H, XIONG Y, et al.Deformable convolutional networks[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2017: 764‑773. [百度学术]
ADELSON E H,ANDERSON C H,BERGEN J R,et al.Pyramid methods in image processing[J].RCA Engineer,1984,29(6): 33‑41. [百度学术]
LOWE D G.Distinctive image features from scale‑invariant keypoints[J].International Journal of Computer Vision,2004,60(2): 91‑110. [百度学术]
DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of IEEE Computer Society Conference on Computer Vision & Pattern Recognition. [S.l.]: IEEE, 2005. [百度学术]
SINGH B, DAVIS L S. An analysis of scale invariance in object detection snip[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 3578‑3587. [百度学术]
SINGH B,NAJIBI M,DAVIS L S.Sniper: Efficient multi‑scale training[EB/OL].(2018‑05‑23)[2018‑12‑13].https://arxiv.org/abs/1805.09300. [百度学术]
REN S,HE K,GIRSHICK R,et al.Faster R‑CNN: Towards real‑time object detection with region proposal networks[EB/OL].(2015‑06‑04)[2016‑01-06].https://arxiv.org/abs/1506.01497. [百度学术]
HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9): 1904-1916. [百度学术]
DAI J, LI Y, HE K, et al.R-FCN: Object detection via region-based fully convolutional networks[EB/OL].(2016-05-20)[2016-06-21].https://arxiv.org/abs/1605.06409. [百度学术]
LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]//Proceedings of European Conference on Computer Vision. Cham: Springer, 2016: 21-37. [百度学术]
CAI Z, FAN Q, FERIS R S, et al. A unified multi-scale deep convolutional neural network for fast object detection[C]//Proceedings of European Conference on Computer Vision. Cham: Springer, 2016: 354-370. [百度学术]
BELL S, ZITNICK C L, BALA K, et al. Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2016: 2874-2883. [百度学术]
KONG T, YAO A, CHEN Y, et al. Hypernet: Towards accurate region proposal generation and joint object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2016: 845-853. [百度学术]
LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 2117-2125. [百度学术]
LIANG Z, SHAO J, ZHANG D, et al. Small object detection using deep feature pyramid networks[C]//Proceedings of Pacific Rim Conference on Multimedia. Cham: Springer, 2018: 554-564. [百度学术]
CAO G, XIE X, YANG W, et al. Feature-fused SSD: Fast detection for small objects[C]//Proceedings of Ninth International Conference on Graphic and Image Processing (ICGIP 2017). Bellingham: SPIE-int SOC Optical Engineering, 2018: 106151E. [百度学术]
LI Z,ZHOU F.FSSD: Feature fusion single shot multibox detector[EB/OL].(2017-12-04)[2018-05-17].https://arxiv.org/abs/1712.00960. [百度学术]
韩松臣,张比浩,李炜,等.基于改进Faster-RCNN的机场场面小目标物体检测算法[J].南京航空航天大学学报,2019,51(6):735-741. [百度学术]
HAN Songchen,ZHANG Bihao,LI Wei,et al.Small target detection in airport scene via modified faster⁃RCNN[J].Journal of Nanjing University of Aeronautics & Astronautics,2019,51(6): 735-741. [百度学术]
NAYAN A A,SAHA J,MOZUMDER A N,et al.Real time detection of small objects[EB/OL].(2020-03-17)[2020-04-14].https://arxiv.org/abs/2003.07442. [百度学术]
LIU Z,GAO G,SUN L,et al.HRDNet: High-resolution detection network for small objects[EB/OL].(2020-06-13)[2020-06-13].https://arxiv.org/abs/2006.07607. [百度学术]
DENG C,WANG M,LIU L,et al.Extended feature pyramid network for small object detection[EB/OL].(2020-05-16)[2020-04-09].https://arxiv.org/abs/2003.07021. [百度学术]
OLIVA A,TORRALBA A.The role of context in object recognition[J].Trends in Cognitive Sciences,2007,11(12): 520-527. [百度学术]
LI J,WEI Y,LIANG X,et al.Attentive contexts for object detection[J].IEEE Transactions on Multimedia,2016,19(5): 944-954. [百度学术]
ZENG X,OUYANG W,YAN J,et al.Crafting gbd-net for object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,40(9): 2109-2123. [百度学术]
TANG X, DU D K, HE Z, et al. Pyramidbox: A context-assisted single shot face detector[C]// Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 797-813. [百度学术]
郑晨斌,张勇,胡杭,等.目标检测强化上下文模型[J].浙江大学学报(工学版),2020,54(3):529-539. [百度学术]
ZHENG Chenbin,ZHANG Yong,HU Hang,et al.Object detection enhanced context model[J].Journal of Zhejiang University (Engineering Science),2020,54(3): 529-539. [百度学术]
DIVVALA S K, HOIEM D, HAYS J H, et al. An empirical study of context in object detection[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2009: 1271-1278. [百度学术]
TORRALBA A, SINHA P. Statistical context priming for object detection[C]// Proceedings of the Eighth IEEE International Conference on Computer Vision. New York: IEEE, 2001: 763-770. [百度学术]
FELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,32(9): 1627-1645. [百度学术]
OUYANG W, WANG X, ZENG X, et al. Deepid-net: Deformable deep convolutional neural networks for object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2015: 2403-2412. [百度学术]
CHEN Z, HUANG S, TAO D. Context refinement for object detection[C]// Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 71-86. [百度学术]
BARNEA E, BEN-SHAHAR O. Exploring the bounds of the utility of context for object detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 7412-7420. [百度学术]
CHEN Z M, JIN X, ZHAO B, et al. Hierarchical context embedding for region-based object detection[C]//Proceedings of European Conference on Computer Vision. Cham: Springer, 2020: 633-648. [百度学术]
张瑞琰,姜秀杰,安军社,等.面向光学遥感目标的全局上下文检测模型设计[J].中国光学,2020,13(73): 138-149. [百度学术]
ZHANG Ruiyan,JIANG Xiujie,AN Junshe, et al.Design of global-contextual detection model for optical remote sensing targets[J].Chinese Optics,2020,13(73): 138-149. [百度学术]
HE K, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2017: 2961-2969. [百度学术]
ZHAO X, LIANG S, WEI Y. Pseudo mask augmented object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 4061-4070. [百度学术]
ZHANG Z, QIAO S, XIE C, et al. Single-shot object detection with enriched semantics[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 5813-5821. [百度学术]
CHEN Q,SONG Z,DONG J,et al.Contextualizing object detection and classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,37(1): 13-27. [百度学术]
GUPTA S,HARIHARAN B,MALIK J.Exploring person context and local scene context for object detection[EB/OL].(2015-11-25)[2015-11-25].https://arxiv.org/abs/1511.08177. [百度学术]
LIU Y, WANG R, SHAN S, et al. Structure inference net: Object detection using scene-level context and instance-level relationships[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 6985-6994. [百度学术]
XU H, JIANG C H, LIANG X, et al. Reasoning-RCNN: Unifying adaptive global reasoning into large-scale object detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 6419-6428. [百度学术]
CHEN X, GUPTA A. Spatial memory for context reasoning in object detection[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2017: 4086-4096. [百度学术]
HU H, GU J, ZHANG Z, et al. Relation networks for object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 3588-3597. [百度学术]
LIM J S,ASTRID M,Yoon H J,et al.Small object detection using context and attention[EB/OL].(2019-12-13)[2019-12-16].https://arxiv.org/abs/1912.06319. [百度学术]
SHEN W, QIN P, ZENG J. An indoor crowd detection network framework based on feature aggregation module and hybrid attention selection module[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Los Alamitos:IEEE, 2019: 82-90. [百度学术]
FU K,LI J,MA L,et al.Intrinsic relationship reasoning for small object detection[EB/OL].(2020-09-02)[2020-09-02].https://arxiv.org/abs/2009.00833. [百度学术]
PATO L V, NEGRINHO R, AGUIAR P M Q. Seeing without looking: Contextual rescoring of object detections for ap maximization[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2020: 14610-14618. [百度学术]
HARIS M,SHAKHNAROVICH G,UKITA N.Task-driven super resolution: Object detection in low-resolution images[EB/OL].(2018-03-30)[2018-03-30].https://arxiv.org/abs/1803.11316. [百度学术]
GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial networks[EB/OL].(2014-06-10)[2014-06-10].https://arxiv.org/abs/1406.2661. [百度学术]
RADFORD A,METZ L,CHINTALA S.Unsupervised representation learning with deep convolutional generative adversarial networks[EB/OL].(2015-11-19)[2016-01-07].https://arxiv.org/abs/1511.06434. [百度学术]
SIXT L,WILD B,LANDGRAF T.Rendergan: Generating realistic labeled data[J].Frontiers in Robotics and AI,2018,5: 66. [百度学术]
WANG X, SHRIVASTAVA A, GUPTA A. A-fast-RCNN: Hard positive generation via adversary for object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 2606-2615. [百度学术]
LI J, LIANG X, WEI Y, et al. Perceptual generative adversarial networks for small object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 1222-1230. [百度学术]
BAI Y, ZHANG Y, DING M, et al. SOD-MTGAN: Small object detection via multi-task generative adversarial network[C]// Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 206-221. [百度学术]
NOH J, BAE W, LEE W, et al. Better to follow, follow to be better: Towards precise supervision of feature super-resolution for small object detection[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2019: 9725-9734. [百度学术]
TYCHSEN-SMITH L, PETERSSON L. Denet: Scalable real-time object detection with directed sparse sampling[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2017: 428-436. [百度学术]
WANG X,CHEN K,HUANG Z, et al.Point linking network for object detection[EB/OL].(2017-06-12)[2017-06-13].https://arxiv.org/abs/1706.03646. [百度学术]
LAW H, DENG J. Cornernet: Detecting objects as paired keypoints[C]// Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 734-750. [百度学术]
LAW H,TENG Y,RUSSAKOVSKY O, et al.Cornernet-lite: Efficient keypoint based object detection[EB/OL].(2017-06-12)[2017-06-13].https://arxiv.org/abs/1706.03646. [百度学术]
DUAN K, BAI S, XIE L, et al. Centernet: Keypoint triplets for object detection[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2019: 6569-6578. [百度学术]
ZHOU X, ZHUO J, KRAHENBUHL P. Bottom-up object detection by grouping extreme and center points[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 850-859. [百度学术]
ZHOU X,WANG D,KRÄHENBÜHL P.Objects as points[EB/OL].(2019-04-16)[2019-04-25].https://arxiv.org/abs/1904.07850. [百度学术]
YANG Z, LIU S, HU H, et al. Reppoints: Point set representation for object detection[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2019: 9657-9666. [百度学术]
KONG T,SUN F,LIU H,et al.Foveabox: Beyound anchor-based object detection[J].IEEE Transactions on Image Processing,2020,29: 7389-7398. [百度学术]
TIAN Z, SHEN C, CHEN H, et al. Fcos: Fully convolutional one-stage object detection[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2019: 9627-9636. [百度学术]
ZHU C, HE Y, SAVVIDES M. Feature selective anchor-free module for single-shot object detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 840-849. [百度学术]
ZHANG S, CHI C, YAO Y, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2020: 9759-9768. [百度学术]
FU J,SUN X,WANG Z,et al.An anchor-free method based on feature balancing and refinement network for multiscale ship detection in SAR images[J].IEEE Transactions on Geoscience and Remote Sensing,2020, 59(2): 1331-1344. [百度学术]
YAN J, ZHAO L, DIAO W, et al.AF-EMS detector: Improve the multi-scale detection performance of the anchor-free detector[J].Remote Sensing,2021,13(2): 160. [百度学术]
ZHANG S, ZHU X, LEI Z, et al. Faceboxes: A CPU real-time face detector with high accuracy[C]//Proceedings of 2017 IEEE International Joint Conference on Biometrics (IJCB). New York: IEEE, 2017: 1-9. [百度学术]
ZHANG S, ZHU X, LEI Z, et al. S3FD: Single shot scale-invariant face detector[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2017: 192-201. [百度学术]
EGGERT C, ZECHA D, BREHM S, et al. Improving small object proposals for company logo detection[C]// Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval. New York: Assoc Computing Machinery, 2017: 167-174. [百度学术]
WANG J, CHEN K, YANG S, et al. Region proposal by guided anchoring[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 2965-2974. [百度学术]
VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]// Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001. New York: IEEE, 2001: 1-9. [百度学术]
LI A,YANG X,ZHANG C.Rethinking classification and localization for cascade R-CNN[EB/OL].(2019-07-27)[2019-07-27].https://arxiv.org/abs/1907.11914. [百度学术]
LIU W, LIAO S, HU W, et al. Learning efficient single-stage pedestrian detectors by asymptotic localization fitting[C]// Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 618-634. [百度学术]
YANG B, YAN J, LEI Z, et al. Craft objects from images[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2016: 6043-6051. [百度学术]
YANG F, CHOI W, LIN Y. Exploit all the layers: Fast and accurate CNN object detector with scale dependent pooling and cascaded rejection classifiers[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. New York: IEEE, 2016: 2129-2137. [百度学术]
GAO M, YU R, LI A, et al. Dynamic zoom-in network for fast object detection in large images[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 6926-6935. [百度学术]
CHEN S,LI J,YAO C,et al.DuBox: No-prior box objection detection via residual dual scale detectors[EB/OL].(2019-04-15)[2019-04-16].https://arxiv.org/abs/1904.06883. [百度学术]
DRENKOW N,BURLINA P,FENDLEY N,et al.Objectness-guided open set visual search and closed set detection[EB/OL].(2020-12-11)[2021-04-14].https://arxiv.org/abs/2012.06509. [百度学术]
YANG F, FAN H, CHU P, et al. Clustered object detection in aerial images[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2019: 8311-8320. [百度学术]
ZHANG J, HUANG J, CHEN X, et al. How to fully exploit the abilities of aerial image detectors[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Los Alamitos:IEEE, 2019: 1-8. [百度学术]
LI C, YANG T, ZHU S, et al. Density map guided object detection in aerial images[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Los Alamitos:IEEE, 2020: 190-191. [百度学术]
LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2017: 2980-2988. [百度学术]
ZHANG H,CHANG H,MA B,et al.Cascade retinanet: Maintaining consistency for single-stage object detection[EB/OL].(2019-07-16)[2019-07-16].https://arxiv.org/abs/1907.06881. [百度学术]
SUN S,YIN Y,WANG X,et al.Multiple receptive fields and small-object-focusing weakly-supervised segmentation network for fast object detection[EB/OL].(2019-04-19)[2019-05-22].https://arxiv.org/abs/1904.12619. [百度学术]
YOO J,LEE H,CHUNG I,et al.Density-based object detection: Learning bounding boxes without ground truth assignment[EB/OL].(2019-11-28)[2020-10-04].https://arxiv.org/abs/1911.12721. [百度学术]
BONDI E, JAIN R, AGGRAWAL P, et al. Birdsai: A dataset for detection and tracking in aerial thermal infrared videos[C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Los Alamitos:IEEE, 2020: 1747-1756. [百度学术]
BRAUN M,KREBS S,FLOHR F,et al.The eurocity persons dataset: A novel benchmark for object detection[EB/OL].(2018-05-18)[2018-06-05].https://arxiv.org/abs/1805.07193. [百度学术]
ZHANG S,XIE Y,WAN J,et al.Widerperson: A diverse dataset for dense pedestrian detection in the wild[J].IEEE Transactions on Multimedia,2019,22(2): 380-393. [百度学术]
NEUMANN L, KARG M, ZHANG S, et al. Nightowls: A pedestrians at night dataset[C]//Proceedings of Asian Conference on Computer Vision. Cham: Springer, 2018: 691-705. [百度学术]
CORDTS M, OMRAN M, RAMOS S, et al. The cityscapes dataset for semantic urban scene understanding[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2016: 3213-3223. [百度学术]
ZHU Z, LIANG D, ZHANG S, et al. Traffic-sign detection and classification in the wild[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2016: 2110-2118. [百度学术]
DOLLÁR P, WOJEK C, SCHIELE B, et al. Pedestrian detection: A benchmark[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2009: 304-311. [百度学术]
WANG L, SHI J, SONG G, et al. Object detection combining recognition and segmentation[C]//Proceedings of Asian Conference on Computer Vision. Berlin, Heidelberg: Springer, 2007: 189-199. [百度学术]
WANG C Y,BOCHKOVSKIY A,LIAO H Y M.Scaled-YOLOv4: Scaling cross stage partial network[EB/OL].(2020-11-16)[2021-02-22].https://arxiv.org/abs/2011.08036. [百度学术]
LENG J,REN Y,JIANG W,et al.Realize your surroundings: Exploiting context information for small object detection[J].Neurocomputing,2021,433: 287-299. [百度学术]
BAI Y, ZHANG Y, DING M, et al. Finding tiny faces in the wild with generative adversarial network[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 21-30. [百度学术]
REDMON J,FARHADI A.Yolov3: An incremental improvement[EB/OL].(2018-04-08)[2018-04-08].https://arxiv.org/abs/1804.02767. [百度学术]
ZHU X, HU H, LIN S, et al. Deformable convnets v2: More deformable, better results[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 9308-9316. [百度学术]
LI Y, CHEN Y, WANG N, et al. Scale-aware trident networks for object detection[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2019: 6054-6063. [百度学术]
TAN Z, NIE X, QIAN Q, et al. Learning to rank proposals for object detection[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2019: 8273-8281. [百度学术]
SONG G, LIU Y, WANG X. Revisiting the sibling head in object detector[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. new york: IEEE, 2020: 11563-11572. [百度学术]
ZHU X,SU W,LU L,et al.Deformable DETR: Deformable transformers for end-to-end object detection[EB/OL].(2020-10-08)[2021-03-18].https://arxiv.org/abs/2010.04159. [百度学术]
TAN M, PANG R, LE Q V. Efficientdet: Scalable and efficient object detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2020: 10781-10790. [百度学术]
YANG S, LUO P, LOY C C, et al. From facial parts responses to face detection: A deep learning approach[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2015: 3676-3684. [百度学术]
ZHANG K,ZHANG Z,LI Z,et al.Joint face detection and alignment using multitask cascaded convolutional networks[J].IEEE Signal Processing Letters,2016,23(10): 1499-1503. [百度学术]
ZHU C, ZHENG Y, LUU K, et al. CMS-RCNN: Contextual multi-scale region-based cnn for unconstrained face detection[C]//Deep learning for biometrics. Cham: Springer, 2017: 57-79. [百度学术]
HU P, RAMANAN D. Finding tiny faces[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 951-959. [百度学术]
NAJIBI M, SAMANGOUEI P, CHELLAPPA R, et al. SSH: Single stage headless face detector[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2017: 4875-4884. [百度学术]
WANG Y,JI X,ZHOU Z,et al.Detecting faces using region-based fully convolutional networks[EB/OL].(2017-09-14)[2017-09-18].https://arxiv.org/abs/1709.05256. [百度学术]
WANG J,YUAN Y,YU G.Face attention network: An effective face detector for the occluded faces[EB/OL].(2017-11-20)[2017-11-22].https://arxiv.org/abs/1711.07246. [百度学术]
LIU Y, SHI M, ZHAO Q, et al. Point in, box out: Beyond counting persons in crowds[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 6469-6478. [百度学术]
ZHANG C,XU X,TU D.Face detection using improved faster RCNN[EB/OL].(2018-02-06)[2018-02-06].https://arxiv.org/abs/1802.02142. [百度学术]
SAM D B,PERI S V,SUNDARARAMAN M N,et al.Locate, size and count: Accurately resolving people in dense crowds via detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020. DOI: 10.1109/TPAMI.2020.2974830. [百度学术]
WANG Y,HOU J,HOU X,et al.A Self-training approach for point-supervised object detection and counting in crowds[J].IEEE Transactions on Image Processing,2021,30: 2876-2887. [百度学术]
GONG Y, YU X, DING Y, et al. Effective fusion factor in FPN for tiny object detection[C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. New York: IEEE, 2021: 1160-1168. [百度学术]
WAN J,DING W,ZHU H,et al.An efficient small traffic sign detection method based on YOLOv3[J].Journal of Signal Processing Systems,2020: DOI: 10.1007/S11265-020-01614-2. [百度学术]
PANG J, CHEN K, SHI J, et al. Libra R-CNN: Towards balanced learning for object detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 821-830. [百度学术]
LU X, LI B, YUE Y, et al. Grid R-CNN[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 7363-7372. [百度学术]
ZHANG X,WAN F,LIU C,et al.Learning to match anchors for visual object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021. DOI: 10.1109/TPAMI.2021.3050494. [百度学术]
SONG S,QUE Z,HOU J,et al.An efficient convolutional neural network for small traffic sign detection[J].Journal of Systems Architecture,2019,97: 269-277. [百度学术]