Generative Adversarial Minority Oversampling
This addresses the problem of class imbalance for deep learning applications, offering a novel oversampling method that is incremental in improving existing techniques.
The paper tackles class imbalance in deep learning by proposing a three-player adversarial game for oversampling minority classes, generating samples near class peripheries to adjust classifier boundaries and reduce misclassification, with extensive experiments on image datasets demonstrating its efficacy.
Class imbalance is a long-standing problem relevant to a number of real-world applications of deep learning. Oversampling techniques, which are effective for handling class imbalance in classical learning systems, can not be directly applied to end-to-end deep learning systems. We propose a three-player adversarial game between a convex generator, a multi-class classifier network, and a real/fake discriminator to perform oversampling in deep learning systems. The convex generator generates new samples from the minority classes as convex combinations of existing instances, aiming to fool both the discriminator as well as the classifier into misclassifying the generated samples. Consequently, the artificial samples are generated at critical locations near the peripheries of the classes. This, in turn, adjusts the classifier induced boundaries in a way which is more likely to reduce misclassification from the minority classes. Extensive experiments on multiple class imbalanced image datasets establish the efficacy of our proposal.