Journal article
Cost-Sensitive learning of deep feature representations from imbalanced data
IEEE Transactions on Neural Networks and Learning Systems, Vol.29(8), pp.3573-3587
2017
Abstract
Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes are abundant, making them an overrepresented majority, and data of other classes are scarce, making them an underrepresented minority. This imbalance makes it challenging for a classifier to appropriately learn the discriminating boundaries of the majority and minority classes. In this paper, we propose a cost-sensitive (CoSen) deep neural network, which can automatically learn robust feature representations for both the majority and minority classes. During training, our learning procedure jointly optimizes the class-dependent costs and the neural network parameters. The proposed approach is applicable to both binary and multiclass problems without any modification. Moreover, as opposed to data-level approaches, we do not alter the original data distribution, which results in a lower computational cost during the training process. We report the results of our experiments on six major image classification data sets and show that the proposed approach significantly outperforms the baseline algorithms. Comparisons with popular data sampling techniques and CoSen classifiers demonstrate the superior performance of our proposed method.
Details
- Title
- Cost-Sensitive learning of deep feature representations from imbalanced data
- Authors/Creators
- S.H. Khan (Author/Creator) - Data61M. Hayat (Author/Creator) - University of CanberraM. Bennamoun (Author/Creator) - The University of Western AustraliaF.A. Sohel (Author/Creator) - Murdoch UniversityR. Togneri (Author/Creator) - The University of Western Australia
- Publication Details
- IEEE Transactions on Neural Networks and Learning Systems, Vol.29(8), pp.3573-3587
- Publisher
- IEEE
- Identifiers
- 991005539974507891
- Copyright
- © 2017 IEEE
- Murdoch Affiliation
- School of Engineering and Information Technology
- Language
- English
- Resource Type
- Journal article
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites
Metrics
50 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
Highly Cited Paper
- Collaboration types
- Domestic collaboration
- Citation topics
- 4 Electrical Engineering, Electronics & Computer Science
- 4.17 Computer Vision & Graphics
- 4.17.128 Deep Visual Recognition
- Web Of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Hardware & Architecture
- Computer Science, Theory & Methods
- Engineering, Electrical & Electronic
- ESI research areas
- Computer Science