Dynamic Curriculum Learning for Imbalanced Data Classification

Human attribute analysis is a challenging task in the field of computer vision. One of the significant difficulties is brought from largely imbalance-distributed data. Conventional techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system. To address this problem, we propose a unified framework called Dynamic Curriculum Learning (DCL) to adaptively adjust the sampling strategy and loss weight in each batch, which results in better ability of generalization and discrimination. Inspired by curriculum learning, DCL consists of two-level curriculum schedulers: (1) sampling scheduler which manages the data distribution not only from imbalance to balance but also from easy to hard; (2) loss scheduler which controls the learning importance between classification and metric learning loss. With these two schedulers, we achieve state-of-the-art performance on the widely used face attribute dataset CelebA and pedestrian attribute dataset RAP.

[1]  Wei Liu,et al.  Multi-Modal Curriculum Learning for Semi-Supervised Image Classification , 2016, IEEE Transactions on Image Processing.

[2]  Taghi M. Khoshgoftaar,et al.  An Empirical Study of the Classification Performance of Learners on Imbalanced and Noisy Software Quality Data , 2007, 2007 IEEE International Conference on Information Reuse and Integration.

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Nitesh V. Chawla,et al.  SPECIAL ISSUE ON LEARNING FROM IMBALANCED DATA SETS , 2004 .

[5]  Haibo He,et al.  ADASYN: Adaptive synthetic sampling approach for imbalanced learning , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[6]  Weilin Huang,et al.  CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images , 2018, ECCV.

[7]  Yang Song,et al.  Class-Balanced Loss Based on Effective Number of Samples , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Szymon Wilk,et al.  Learning from Imbalanced Data in Presence of Noisy and Borderline Examples , 2010, RSCTC.

[9]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[10]  Kai Ming Ting,et al.  A Comparative Study of Cost-Sensitive Boosting Algorithms , 2000, ICML.

[11]  Shaogang Gong,et al.  Class Rectification Hard Mining for Imbalanced Deep Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[12]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[13]  Shiguang Shan,et al.  Self-Paced Curriculum Learning , 2015, AAAI.

[14]  Yunqian Ma,et al.  Imbalanced Learning: Foundations, Algorithms, and Applications , 2013 .

[15]  Shaogang Gong,et al.  Attribute Recognition by Joint Recurrent Learning of Context and Correlation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[16]  Ioannis A. Kakadiaris,et al.  Curriculum Learning of Visual Attribute Clusters for Multi-Task Classification , 2017, Pattern Recognit..

[17]  Taghi M. Khoshgoftaar,et al.  Supervised Neural Network Modeling: An Empirical Investigation Into Learning From Imbalanced Data With Labeling Errors , 2010, IEEE Transactions on Neural Networks.

[18]  Nitesh V. Chawla,et al.  SMOTEBoost: Improving Prediction of the Minority Class in Boosting , 2003, PKDD.

[19]  Seetha Hari,et al.  Learning From Imbalanced Data , 2019, Advances in Computer and Electrical Engineering.

[20]  Taghi M. Khoshgoftaar,et al.  Knowledge discovery from imbalanced and noisy data , 2009, Data Knowl. Eng..

[21]  Yong Jae Lee,et al.  Learning the easy things first: Self-paced visual category discovery , 2011, CVPR 2011.

[22]  Tomasz Maciejewski,et al.  Local neighbourhood extension of SMOTE for mining imbalanced data , 2011, 2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[23]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[24]  Changyin Sun,et al.  ODOC-ELM: Optimal decision outputs compensation-based extreme learning machine for classifying imbalanced data , 2016, Knowl. Based Syst..

[25]  Hui Han,et al.  Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning , 2005, ICIC.

[26]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[27]  Zhi-Hua Zhou,et al.  Exploratory Undersampling for Class-Imbalance Learning , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[28]  Lars Schmidt-Thieme,et al.  Cost-sensitive learning methods for imbalanced data , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[29]  Xiaogang Wang,et al.  HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[30]  Taghi M. Khoshgoftaar,et al.  Comparing Boosting and Bagging Techniques With Noisy and Imbalanced Data , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[31]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[32]  Yan Wang,et al.  DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Zhi-Hua Zhou,et al.  Ieee Transactions on Knowledge and Data Engineering 1 Training Cost-sensitive Neural Networks with Methods Addressing the Class Imbalance Problem , 2022 .

[34]  Carlos D. Castillo,et al.  Doing the Best We Can With What We Have: Multi-Label Balancing With Selective Learning for Attribute Prediction , 2018, AAAI.

[35]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[36]  Junjie Yan,et al.  Localization Guided Learning for Pedestrian Attribute Recognition , 2018, BMVC.

[37]  Pedro Antonio Gutiérrez,et al.  A dynamic over-sampling procedure based on sensitivity for multi-class problems , 2011, Pattern Recognit..

[38]  Shirui Pan,et al.  Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence Graph Classification with Imbalanced Class Distributions and Noise ∗ , 2022 .

[39]  Lance Chun Che Fung,et al.  Classification of Imbalanced Data by Combining the Complementary Neural Network and SMOTE Algorithm , 2010, ICONIP.

[40]  Mohammed Bennamoun,et al.  Cost-Sensitive Learning of Deep Feature Representations From Imbalanced Data , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[41]  黄凯奇,et al.  Multi-attribute Learning for Pedestrian Attribute Recognition in Surveillance Scenarios , 2015 .

[42]  Ioannis A. Kakadiaris,et al.  Deep Imbalanced Attribute Classification using Visual Attention Aggregation , 2018, ECCV.

[43]  John Langford,et al.  Cost-sensitive learning by cost-proportionate example weighting , 2003, Third IEEE International Conference on Data Mining.

[44]  Jianjun Wang,et al.  Margin calibration in SVM class-imbalanced learning , 2009, Neurocomputing.

[45]  Xindong Wu,et al.  Active Learning With Imbalanced Multiple Noisy Labeling , 2015, IEEE Transactions on Cybernetics.

[46]  H. Ahn,et al.  Decision threshold adjustment in class prediction , 2006, SAR and QSAR in environmental research.

[47]  Christoph H. Lampert,et al.  Curriculum learning of multiple tasks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[48]  Deva Ramanan,et al.  Self-Paced Learning for Long-Term Tracking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[49]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[50]  Yan Wang,et al.  Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model , 2017, BMVC.

[51]  Taeho Jo,et al.  A Multiple Resampling Method for Learning from Imbalanced Data Sets , 2004, Comput. Intell..

[52]  Shaogang Gong,et al.  Imbalanced Deep Learning by Minority Class Incremental Rectification , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[53]  Kaiqi Huang,et al.  A Richly Annotated Dataset for Pedestrian Attribute Recognition , 2016, ArXiv.

[54]  Yanqing Zhang,et al.  SVMs Modeling for Highly Imbalanced Classification , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[55]  Longbing Cao,et al.  Training deep neural networks on imbalanced data sets , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[56]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[57]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[58]  Antônio de Pádua Braga,et al.  Novel Cost-Sensitive Approach to Improve the Multilayer Perceptron Performance on Imbalanced Data , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[59]  Robert C. Holte,et al.  C4.5, Class Imbalance, and Cost Sensitivity: Why Under-Sampling beats Over-Sampling , 2003 .

[60]  Chen Huang,et al.  Deep Imbalanced Learning for Face Recognition and Attribute Prediction , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[61]  Chen Huang,et al.  Learning Deep Representation for Imbalanced Classification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[62]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.