Imbalance Rectification in Deep Logistic Regression for Multi-Label Image Classification Using Random Noise Samples
Authors: 
Wenjin Yan, 
Ruixuan Li, Jun Wang, Yuhua Li, Jinyang Wang, Pan Zhou, Xiwu GuAuthors Info & Claims
Wenjin Yan, Ruixuan Li, Jun Wang, Yuhua Li, Jinyang Wang, Pan Zhou, Xiwu GuAuthors Info & ClaimsPages 1131 - 1140
Abstract
Logistic regression (LR) is the most commonly used loss function in multi-label image classification. However, it suffers from class imbalance problem caused by the huge difference in quantity between positive and negative samples as well as between different classes. First, we find that feeding randomly generated noise samples into an LR classifier is an effective way to detect class imbalances, and further define an informative imbalance metric named inference tendency based on noise sample analysis. Second, we design an efficient moving average based method for calculating inference tendency, which can be easily done during training with negligible overhead. Third, two novel rectification methods called extremum shift (ES) and tendency constraint (TC) are designed to offset or constrain inference tendency in the loss function, and mitigate class imbalances significantly. Finally, comparative experiments with Resnet on Microsoft COCO, NUS-WIDE and DeepFashion demonstrate the effectiveness of inference tendency and the superiority of our approach over the baseline LR and several state-of-the-art alternatives.
References
[1]
Nitesh V. Chawla, KevinW. Bowyer, Lawrence O. Hall, andW. Philip Kegelmeyer. 2006. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research (2006), 321--357.
[2]
Tianshui Chen, Zhouxia Wang, Guanbin Li, and Liang Lin. 2018. Recurrent attentional reinforcement learning for multi-label image recognition. In Thirty- Second AAAI Conference on Artificial Intelligence. AAAI.
[3]
Tat-Seng Chua, Jinhui Tang, Richang Hong, Haojie Li, Zhiping Luo, and Yantao Zheng. 2009. NUS-WIDE: a real-world web image database from National University of Singapore. In Proceedings of the ACM international conference on image and video retrieval. ACM, 48.
[4]
Jia Deng,Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE.
[5]
Qi Dong, Shaogang Gong, and Xiatian Zhu. 2017. Class rectification hard mining for imbalanced deep learning. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, 1851--1860.
[6]
Qi Dong, Xiatian Zhu, and Shaogang Gong. 2019. Single-Label Multi-Class Image Classification by Deep Logistic Regression. In Thirty-Third AAAI Conference on Artificial Intelligence. AAAI.
[7]
Chris Drummond, Robert C Holte, and others. 2003. C4. 5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling. In Workshop on learning from imbalanced datasets II. Citeseer, 1--8.
[8]
Chris Drummond, Robert C Holte, and others. 2003. C4. 5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling. In Workshop on learning from imbalanced datasets. Citeseer, 1--8.
[9]
Haibo He and Edwardo A Garcia. 2008. Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering (2008), 1263--1284.
[10]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 770--778.
[11]
Timothy M Hospedales, Shaogang Gong, and Tao Xiang. 2013. Finding rare classes: Active learning with generative and discriminative models. IEEE transactions on knowledge and data engineering (2013), 374--386.
[12]
Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In International Conference on Machine Learning. ACM, 448--456.
[13]
Nathalie Japkowicz and Shaju Stephen. 2002. The class imbalance problem: A systematic study. Intelligent data analysis (2002), 429--449.
[14]
Nikhil Ketkar. 2017. Introduction to pytorch. In Deep learning with python. 195--208.
[15]
Bartosz Krawczyk. 2016. Learning from imbalanced data: open challenges and future directions. Progress in Artificial Intelligence (2016), 221--232.
[16]
Buyu Li, Yu Liu, and Xiaogang Wang. 2019. Gradient Harmonized Single-stage Detector. In Thirty-Third AAAI Conference on Artificial Intelligence. AAAI.
[17]
Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision. IEEE, 2980--2988.
[18]
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollar, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In European conference on computer vision. Springer, 740--755.
[19]
Charles X. Ling and Victor S. Sheng. 2010. Cost-Sensitive Learning. In Encyclopedia of Machine Learning. Springer, 285--289.
[20]
Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016. Ssd: Single shot multibox detector. In European conference on computer vision. Springer, 21--37.
[21]
Ziwei Liu, Ping Luo, Shi Qiu, Xiaogang Wang, and Xiaoou Tang. 2016. Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 1096--1104.
[22]
Tomasz Maciejewski and Jerzy Stefanowski. 2011. Local neighbourhood extension of SMOTE for mining imbalanced data. In IEEE Symposium on Computational Intelligence and Data Mining. IEEE, 104--111.
[23]
Maxime Oquab, Leon Bottou, Ivan Laptev, and Josef Sivic. 2014. Learning and transferring mid-level image representations using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 1717--1724.
[24]
Bharat Singh, Mahyar Najibi, and Larry S Davis. 2018. SNIPER: Efficient multiscale training. In Advances in Neural Information Processing Systems. NIPS, 9310-- 9320.
[25]
Grigorios Tsoumakas and Ioannis Katakis. 2007. Multi-label classification: An overview. International Journal of Data Warehousing and Mining (2007), 1--13.
[26]
Senzhang Wang, Zhoujun Li, Wenhan Chao, and Qinghua Cao. 2012. Applying adaptive over-sampling technique based on data density and cost-sensitive SVM to imbalanced learning. In The 2012 International Joint Conference on Neural Networks. IEEE, 1--8.
[27]
Gary M Weiss. 2004. Mining with rarity: a unifying framework. ACM Sigkdd Explorations Newsletter (2004), 7--19.
[28]
Michal Woniak, Manuel Graña, and Emilio Corchado. 2014. A survey of multiple classifier systems as hybrid systems. Information Fusion (2014), 3--17.
[29]
Xi-Zhu Wu and Zhi-Hua Zhou. 2017. A unified view of multi-label performance measures. In Proceedings of the 34th International Conference on Machine Learning. JMLR.org, 3780--3788.
[30]
Feng Zhu, Hongsheng Li, Wanli Ouyang, Nenghai Yu, and Xiaogang Wang. 2017. Learning spatial regularization with image-level supervisions for multi-label image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 5513--5522.
Index Terms
- Imbalance Rectification in Deep Logistic Regression for Multi-Label Image Classification Using Random Noise Samples
Recommendations
Class Imbalance Oriented Logistic Regression
CYBERC '14: Proceedings of the 2014 International Conference on Cyber-Enabled Distributed Computing and Knowledge DiscoveryClass-imbalance is quite common in real world. For the imbalanced class distribution, traditional state-of-the-art classifiers do not work well on imbalanced data sets. In this paper, we apply logistic regression model to class-imbalance problem, and ...
Multi-label sampling based on local label imbalance
Highlights- The local imbalance is more crucial than the global one in multi-label data.
- ...
AbstractClass imbalance is an inherent characteristic of multi-label data that hinders most multi-label learning methods. One efficient and flexible strategy to deal with this problem is to employ sampling techniques before training a multi-...
A multi-objective optimisation approach for class imbalance learning
Class imbalance limits the performance of most learning algorithms since they cannot cope with large differences between the number of samples in each class, resulting in a low predictive accuracy over the minority class. In this respect, several papers ...
Comments
Information & Contributors
Information
Published In
November 2019
3373 pages
ISBN:9781450369763
DOI:10.1145/3357384
- General Chairs:
- Wenwu Zhu,
- Dacheng Tao,
- Xueqi Cheng,
- Program Chairs:
- Peng Cui,
- Elke Rundensteiner,
- David Carmel,
- Qi He,
- Jeffrey Xu Yu
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 03 November 2019
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Natural Science Foundation of China
Conference
CIKM '19: The 28th ACM International Conference on Information and Knowledge Management
November 3 - 7, 2019
Beijing, China
Acceptance Rates
CIKM '19 Paper Acceptance Rate 202 of 1,031 submissions, 20%;
Overall Acceptance Rate 1,861 of 8,427 submissions, 22%
Upcoming Conference
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 257Total Downloads
- Downloads (Last 12 months)12
- Downloads (Last 6 weeks)1
Reflects downloads up to 03 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in