Enhance Via Decoupling: Improving Multi-Label Classifiers With Variational Feature Augmentation

Multi-label classification remains a challenging problem due to the inherent label imbalance issue, which brings over-fitting of minor categories to modern deep models. In this paper, to tackle this issue, we propose a novel method named Variational Feature Augmentation (VFA) to enhance the deep neural networks for multi-label classification. Our method decouples the feature vectors extracted by the backbone network into multiple low-dimensional spaces via a novely proposed Variational Feature Decoupling Module. The decoupled feature vectors are then re-combined with a shuffle operation and a Feature Augmentation Layer to enrich the minor co-occurrence relations, mitigating the label imbalance. Different from most other methods, VFA does not modify the network architecture or introduce extra computation cost in inference phase. We conduct comprehensive experiments on four benchmarks of two visual multi-label classification tasks, pedestrian attribute recognition and multi-label image recognition, and the results demonstrate the effectiveness and generality of the proposed VFA.