|Table of Contents|

Research Advance in Long-tailed Recognition(PDF)

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

Issue:
2022年02期
Page:
63-72
Research Field:
计算机科学与技术
Publishing date:

Info

Title:
Research Advance in Long-tailed Recognition
Author(s):
Zhang Ming1; 2; Zhai Junhai1; 2; Xu Lei1; 2; Gao Guangyuan1; 2
(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)
Keywords:
deep learning; long-tailed recognition; computer vision; research method; neural network
PACS:
TP181
DOI:
10.3969/j.issn.1672-1292.2022.02.010
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.

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.

Memo

Memo:
-
Last Update: 1900-01-01