[1]张 明,翟俊海,许 垒,等.长尾识别研究进展[J].南京师范大学学报(工程技术版),2022,(02):063-72.[doi:10.3969/j.issn.1672-1292.2022.02.010]
 Zhang Ming,Zhai Junhai,Xu Lei,et al.Research Advance in Long-tailed Recognition[J].Journal of Nanjing Normal University(Engineering and Technology),2022,(02):063-72.[doi:10.3969/j.issn.1672-1292.2022.02.010]
点击复制

长尾识别研究进展
分享到:

南京师范大学学报(工程技术版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2022年02期
页码:
063-72
栏目:
计算机科学与技术
出版日期:
2022-06-30

文章信息/Info

Title:
Research Advance in Long-tailed Recognition
文章编号:
1672-1292(2022)02-0063-10
作者:
张 明12翟俊海12许 垒12高光远12
(1.河北大学数学与信息科学学院,河北 保定 071002)(2.河北大学河北省机器学习与计算智能重点实验室,河北 保定 071002)
Author(s):
Zhang Ming12Zhai Junhai12Xu Lei12Gao Guangyuan12
(1.School of Mathematics and Information Science,Hebei University,Baoding 071002,China)(2.Hebei Key Laboratory of Machine Learning and Computational Intelligence,Hebei University,Baoding 071002,China)
关键词:
深度学习长尾识别计算机视觉研究方法神经网络
Keywords:
deep learninglong-tailed recognitioncomputer visionresearch methodneural network
分类号:
TP181
DOI:
10.3969/j.issn.1672-1292.2022.02.010
文献标志码:
A
摘要:
长尾识别是目前深度学习领域最热门的研究方向之一,长尾识别的工作重点是解决长尾分布数据的计算机视觉识别任务. 长尾分布的显著特征为2-8分布,即20%的类占据80%的样本. 将少数几个类占据了大部分数据的类称之为头部类; 而大多数类占据了很少部分数据的类称之为尾部类. 首先,列举解决长尾识别问题的各种方法. 然后,将其划分为重采样、重加权、迁移学习、解耦特征学习和分类器学习以及其他方法进行阐述. 最后,阐述对相关方法的理解.
Abstract:
Long tail recognition is one of the most popular research directions in the field of deep learning. The focus of long tail recognition is to solve the computer vision recognition task of long-tail distributed data. The prominent feature of the long-tail distribution is the 2-8 distribution,that is,20% of the classes account for 80% of the sample. We call a class with a few classes that make up most of the data a header class. Classes where most classes occupy a small portion of the data are called tail classes. Firstly, various methods are introduced to solve the problem of long tail recognition. Then, they are divided into resampling,re-weighting,transfer learning,decoupling feature learning,classifier learning and other methods. Finally, our understanding of the related methods are introduced.

参考文献/References:

[1] KRIZHEVSKY A,SUTSKEVER I,HINTON G E. Imagenet classification with deep convolutional neural networks[C]//Conference and Workshop on Neural Information Processing Systems. California,USA,2012:1097-1105.
[2]GIRSHICK R,DONAHUE J,DARRELL T,et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition. Columbus,OH,USA,2014:580-587.
[3]MASI I,WU Y,HASSNER T,et al. Deep face recognition:A survey[J/OL]. http://arXiv.org/abs/1804.06655v8.
[4]JAMAL M A,BROWN M,YANG M H,et al. Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective[C]//IEEE Conference on Computer Vision and Pattern Recognition. Seattle,USA,2020:7607-7616.
[5]JAPKOWICZ N,STEPHEN S. The class imbalance problem:a systematic study[J]. Intelligent Data Analysis,2002,6(5):429-449.
[6]SHEN LI,LIN Z C,HUANG Q M. Relay backpropagation for effective learning of deep convolutional neural networks[C]//European Conference on Computer Vision. Amsterdam,Netherlands:Springer,2016:467-482.
[7]HE H,GARCIA E A. Learning from imbalanced data[J]. IEEE Transactions on Knowledge and Data Engineering,2009,21(9):1263-1284.
[8]HAN H,WANG W Y,MAO B H. Borderline-smote:a new over-sampling method in imbalanced data sets learning[J]. Lecture Notes in Computer Science,2005:878-887.
[9]GAO H,SHOU Z,ZAREIAN A,et al. Low-shot learning via covariance-preserving adversarial augmentation networks[J]. Neural Information Processing Systems,2018,31:975-985.
[10]MACIEJEWSKI T,STEFANOWSKI J. Local neighbourhood extension of smote for mining imbalanced data[C]//IEEE International Conference on Data Mining. Paris,France,2011:104-111.
[11]CHAWLA N V,BOWYER K W,HALL L O,et al. Smote:synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research,2002:321-357.
[12]COVER T,HART P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory,1967,13(1):21-27.
[13]GOODFELLOW I J,POUGET A J,MIRZA M,et al. Generative adversarial networks[J]. Advances in Neural Information Processing Systems,2014,3:2672-2680.
[14]DRUMMOND C,HOLTE R C. C4.5,Class imbalance,and cost sensitivity:Why under-sampling beats over-sampling[C]//Workshop on Learning from Imbalanced Datasets II. Washington,DC,USA,2003:1-8.
[15]BUDA M,MAKI A,MAZUROWSKI M A. A systematic study of the class imbalance problem in convolutional neural networks[J]. Neural Networks,2018,106:249-259.
[16]LIU X Y,WU J,ZHOU Z H. Exploratory undersampling for class-imbalance learning[J]. IEEE Transactions on Systems,Man,and Cybernetics,Part B(Cybernetics),2008,39(2):539-550.
[17]TING K M. A comparative study of cost-sensitive boosting algorithms[C]//International Conference on Machine Learning. Ithaca,New York,USA,2000:983-990.
[18]ZADROZNY B,LANGFORD J,ABE N. Cost-sensitive learning by cost-proportionate example weighting[C]//Third IEEE International Conference on Data Mining. Melbourne,FL,USA,2003:435.
[19]MIKOLOV T,SUTSKEVER I,CHEN K,et al. Distributed representations of words and phrases and their compositionality[J]. Advances in Neural Information Processing Systems,2013:3111-3119.
[20]HUANG C,LI Y N,TANG X O,et al. Learning deep representation for imbalanced classification[C]//IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA,2016:5375-5384.
[21]CUI Y,JIA M L,LIN T Y,et al. Class-balanced loss based on effective number of samples[C]//IEEE Conference on Computer Vision and Pattern Recognition. Los Angeles,USA,2019:9268-9277.
[22]LI B,LIU Y,WANG X. Gradient harmonized single-stage detector[C]//AAAI conference on artificial intelligence. Honolulu,Hawaii,USA,2019,33(1):8577-8584.
[23]LIN T Y,GOYAL P,GIRSHICK R,et al. Focal loss for dense object detection[C]//International Conference on Computer Vision. Venice,Italy,2017:2980-2988.
[24]DONG Q,GONG S G,ZHU X T,et al. Class rectification hard mining for imbalanced deep learning[C]//IEEE International Conference on Computer Vision. Venice,USA,2017:1869-1878.
[25]TAN J R,WANG C B,LI B Y,et al. Equalization loss for long-tailed object recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Seattle,USA,2020:11659-11668.
[26]CAO K D,WEI C L,GAIDON A,et al. Learning imbalanced datasets with label-distribution-aware margin loss[C]//Neural Information Processing Systems. Vancouver,Canada,2019:1-18.
[27]ZHOU Y C,HU Q H,WANG Y,et al. Deep super-class learning for long-tail distributed image classification[J]. Pattern Recognition,2018,80:118-128.
[28]MENON A K,JAYASUMANA S,RAWAT A S,et al. Long-tail learning via logit adjustment[J/OL]. http://arXiv.org/abs/2007.07314.
[29]MAHAJAN D,GIRSHICK R,RAMANATHAN V,et al. Exploring the limits of weakly supervised pretraining[C]//European Conference on Computer Vision. Munich,Germany,2018:181-196.
[30]YIN X,YU X,SOHN K,et al. Feature transfer learning for face recognition with under-represented data[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Long Beach,Los Angeles,USA,2019:5704-5713.
[31]PAN S J,YANG Q. A survey on transfer learning[J]. IEEE transactions on knowledge and data engineering,2010,22(10):1345-1359.
[32]ZAMIR A R,SAX A,SHEN W. Taskonomy:disentangling task transfer learning[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA,2018.
[33]WANG Y X,DEVA R,MARTIAL H,et al. Learning to model the tail[C]//Conference and Workshop on Neural Information Processing Systems. California,USA,2017:7032-7042.
[34]MOSTAFA M E,PRAVEEN K,LUIGI M. Identification and characterization of information-networks in long-tail data collections[J]. Environmental Modelling & Software,2017:100-111.
[35]ZHOU B Y,CUI Q,WEI X S,et al. BBN:Bilateral-branch network with cumulative learning for long-tailed visual recognition[C]//Computer Vision and Pattern Recognition. Seattle,USA,2020:9716-9724.
[36]KANG B Y,XIE S,ROHRBACH M,et al. Decoupling representation and classifier for long-tailed recognition[C]//International Conference on Learning Representations. Montreal,USA,2020.
[37]ZHU X X,ANGUELOV D,RAMANAN D,et al. Capturing long-tail distributions of object subcategories[C]//IEEE Conference on Computer Vision and Pattern Recognition. Columbus,USA,2014:915-922.
[38]SINHA S,EBRAHIMI S,DARRELL T,et al. Variational adversarial active learning[C]//IEEE International Conference on Computer Vision. Seoul,Korean,2019:5972-5981.
[39]MA Y H,KAN M N,SHAN S G,et al. Learning deep face representation with long-tail data:anaggregate-and-disperse approach[J]. Pattern Recognition Letters,2020,133:48-54.
[40]TONG W,LI Y F. Does tail label help for large-scale multi-label learning[J]. IEEE Transactions on Neural Networks and Learning Systems,2020,31(7):2315-2324.
[41]GUPTA A,DOLLAR P,GIRSHICK R. LVIS:A dataset for large vocabulary instance segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition.Los Angeles,USA,2019.
[42]ZHANG X,FANG Z Y,WEN Y D,et al. Range loss for deep face recognition with long-tailed training data[C]//IEEE International Conference on Computer Vision. Venice,USA,2017:5419-5428.
[43]WEN Y,ZHANG K,LI Z,et al. A discriminative feature learning approach for deep face recognition[C]//European Conference on Computer Vision. Amsterdam,Netherlands,2016:499-515.
[44]TAIGMAN Y,YANG M,RANZATO M,et al. Deepface:closing the gapto human-level performance in face verification[C]//IEEE Conference on Computer Vision and Pattern Recognition. Columbus,USA,2014:1701-1708.
[45]LIU Z W,MIAO Z Q,ZHAN X H,et al. Large-scale long-tailed recognition in an open world[C]//IEEE Conference on Computer Vision and Pattern Recognition. Los Angeles,USA,2019:2532-2541.
[46]HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA,2016.
[47]LIU J L,SUN Y F,HAN C C,et al. Deep representation learning on long-tailed data:a learnable embedding augmentation perspective[C]//IEEE Conference on Computer Vision and Pattern Recognition. Seattle,USA,2020:2967-2976.
[48]HUANG H,LI D,ZHANG Z,et al. Adversarially occluded samples for person re-identification[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA,2018:5098-5107.
[49]XU J,ZHAO R,ZHU F,et al. Attention-aware compositional network for person reidentification[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA,2018:2119-2128.
[50]ZHU L C,YANG Y. Inflated episodic memory with region self-attention for long-tailed visual recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition. Seattle,USA,2020:4343-4352.
[51]ZHANG J J,LIU L Q,WANG P,ET AL. To balance or not to balance:a simple-yet-effective approach for learning with long-tailed distributions[C]//IEEE Conference on Computer Vision and Pattern Recognition. Seattle,USA,2020.
[52]WANG X D,LIAN L,MIAO Z,et al. Long-tailed recognition by routing diverse distribution-aware experts[J/OL]. http://arXiv.org/abs/2010.01809.

相似文献/References:

[1]程显毅,胡海涛,季国华,等.基于深度学习监控场景下的多尺度目标检测算法研究[J].南京师范大学学报(工程技术版),2018,18(03):033.[doi:10.3969/j.issn.1672-1292.2018.03.005]
 Cheng Xianyi,Hu Haitao,Ji Guohua,et al.Research on Algorithm of Multi-Scale Target DetectionBased on Deep Learning in Monitoring Scenario[J].Journal of Nanjing Normal University(Engineering and Technology),2018,18(02):033.[doi:10.3969/j.issn.1672-1292.2018.03.005]
[2]陈 扬,曾 诚,程 成,等.一种基于CNN的足迹图像检索与匹配方法[J].南京师范大学学报(工程技术版),2018,18(03):039.[doi:10.3969/j.issn.1672-1292.2018.03.006]
 Chen Yang,Zeng Cheng,Cheng Cheng,et al.A CNN-based Approach to Footprint Image Retrieval and Matching[J].Journal of Nanjing Normal University(Engineering and Technology),2018,18(02):039.[doi:10.3969/j.issn.1672-1292.2018.03.006]
[3]王俊淑,张国明,胡 斌.基于深度学习的推荐算法研究综述[J].南京师范大学学报(工程技术版),2018,18(04):033.[doi:10.3969/j.issn.1672-1292.2018.04.006]
 Wang Junshu,Zhang Guoming,Hu Bin.A Survey of Deep Learning Based Recommendation Algorithms[J].Journal of Nanjing Normal University(Engineering and Technology),2018,18(02):033.[doi:10.3969/j.issn.1672-1292.2018.04.006]
[4]郝 坤,张天坤,史振威.基于时空特征的热带气旋强度预测方法[J].南京师范大学学报(工程技术版),2019,19(03):001.[doi:10.3969/j.issn.1672-1292.2019.03.001]
 Hao Kun,Zhang Tiankun,Shi Zhenwei.An Tropical Cyclone Intensity Prediction MethodBased on Spatial-Temporal Features[J].Journal of Nanjing Normal University(Engineering and Technology),2019,19(02):001.[doi:10.3969/j.issn.1672-1292.2019.03.001]
[5]任媛媛,张显峰,马永建,等.基于卷积神经网络的无人机遥感影像农村建筑物目标检测[J].南京师范大学学报(工程技术版),2019,19(03):029.[doi:10.3969/j.issn.1672-1292.2019.03.005]
 Ren Yuanyuan,Zhang Xianfeng,Ma Yongjian,et al.Target Detection of Rural Buildings in UAV Remote Sensing ImagesBased on Convolutional Neural Network[J].Journal of Nanjing Normal University(Engineering and Technology),2019,19(02):029.[doi:10.3969/j.issn.1672-1292.2019.03.005]
[6]许博鸣,刘晓峰,业巧林,等.基于卷积神经网络面向自然场景建筑物识别技术的移动端应用[J].南京师范大学学报(工程技术版),2019,19(03):037.[doi:10.3969/j.issn.1672-1292.2019.03.006]
 Xu Boming,Liu Xiaofeng,Ye Qiaolin,et al.A Convolutional Neural Network Based on Mobile Application forIdentification of Buildings in Natural Scene[J].Journal of Nanjing Normal University(Engineering and Technology),2019,19(02):037.[doi:10.3969/j.issn.1672-1292.2019.03.006]
[7]吴燕如,珠 杰,管美静.基于深度学习的藏文现代印刷物版面检测技术研究[J].南京师范大学学报(工程技术版),2021,(01):044.[doi:10.3969/j.issn.1672-1292.2021.01.007]
 Wu Yanru,Zhu Jie,Guan Meijing.Research on Layout Inspection Technology of ModernTibetan Prints Based on Deep Learning[J].Journal of Nanjing Normal University(Engineering and Technology),2021,(02):044.[doi:10.3969/j.issn.1672-1292.2021.01.007]
[8]梁秦嘉,刘 怀,陆 飞.基于改进YOLOv3模型的交通视频目标检测算法研究[J].南京师范大学学报(工程技术版),2021,(02):047.[doi:10.3969/j.issn.1672-1292.2021.02.008]
 Liang Qinjia,Liu Huai,Lu Fei.Traffic Video Target Detection Algorithm Based on Improved YOLOv3[J].Journal of Nanjing Normal University(Engineering and Technology),2021,(02):047.[doi:10.3969/j.issn.1672-1292.2021.02.008]
[9]苏 叶,李 婧,徐寅林.手骨X光片骨龄预测中图像预处理的研究[J].南京师范大学学报(工程技术版),2021,(02):054.[doi:10.3969/j.issn.1672-1292.2021.02.009]
 Su Ye,Li Jing,Xu Yinlin.Research on Image Preprocessing in Predicting the Bone Age ofHand Bone X-ray Films[J].Journal of Nanjing Normal University(Engineering and Technology),2021,(02):054.[doi:10.3969/j.issn.1672-1292.2021.02.009]
[10]王立凯,曲维光,魏庭新,等.基于深度学习的中文零代词识别[J].南京师范大学学报(工程技术版),2021,(04):019.[doi:10.3969/j.issn.1672-1292.2021.04.004]
 Wang Likai,Qu Weiguang,Wei Tingxin,et al.Identification of Chinese Zero Pronouns Based on Deep Learning[J].Journal of Nanjing Normal University(Engineering and Technology),2021,(02):019.[doi:10.3969/j.issn.1672-1292.2021.04.004]

备注/Memo

备注/Memo:
收稿日期:2021-08-31.
基金项目:河北省科技计划重点研发项目(19210310D)、河北省自然科学基金项目(F2021201020).
通讯作者:翟俊海,博士,教授,研究方向:机器学习、云计算与大数据处理、深度学习. E-mail:mczjh@126.com
更新日期/Last Update: 1900-01-01