Data Augmentation Imbalance For Imbalanced Attribute Classification
This addresses data imbalance for fine-grained multi-label classification in pedestrian attribute recognition, but it is incremental as it builds on existing re-sampling methods.
The paper tackles data imbalance in multi-label pedestrian attribute recognition by proposing a data augmentation imbalance (DAI) algorithm that over-samples and under-samples to enhance discrimination of fewer attributes, achieving state-of-the-art results on PA-100K and PETA datasets.
Pedestrian attribute recognition is an important multi-label classification problem. Although the convolutional neural networks are prominent in learning discriminative features from images, the data imbalance in multi-label setting for fine-grained tasks remains an open problem. In this paper, we propose a new re-sampling algorithm called: data augmentation imbalance (DAI) to explicitly enhance the ability to discriminate the fewer attributes via increasing the proportion of labels accounting for a small part. Fundamentally, by applying over-sampling and under-sampling on the multi-label dataset at the same time, the thought of robbing the rich attributes and helping the poor makes a significant contribution to DAI. Extensive empirical evidence shows that our DAI algorithm achieves state-of-the-art results, based on pedestrian attribute datasets, i.e. standard PA-100K and PETA datasets.