Weak-supervision for Deep Representation Learning under Class Imbalance
This addresses class imbalance in deep learning, particularly for large numbers of classes, but is incremental as it builds on existing over-sampling methods.
The paper tackles class imbalance in deep learning by extending a deep over-sampling framework with automatically-generated abstract-labels to enhance representation learning, achieving substantial improvements on image classification benchmarks with imbalanced classes.
Class imbalance is a pervasive issue among classification models including deep learning, whose capacity to extract task-specific features is affected in imbalanced settings. However, the challenges of handling imbalance among a large number of classes, commonly addressed by deep learning, have not received a significant amount of attention in previous studies. In this paper, we propose an extension of the deep over-sampling framework, to exploit automatically-generated abstract-labels, i.e., a type of side-information used in weak-label learning, to enhance deep representation learning against class imbalance. We attempt to exploit the labels to guide the deep representation of instances towards different subspaces, to induce a soft-separation of inherent subtasks of the classification problem. Our empirical study shows that the proposed framework achieves a substantial improvement on image classification benchmarks with imbalanced among large and small numbers of classes.