Dynamic Curriculum Learning for Imbalanced Data Classification
This addresses the challenge of imbalanced data in computer vision for tasks like face and pedestrian attribute analysis, offering an incremental improvement over existing methods.
The paper tackles the problem of imbalanced data classification in human attribute analysis by proposing Dynamic Curriculum Learning (DCL), a framework that adaptively adjusts sampling and loss strategies, achieving state-of-the-art performance on CelebA and RAP datasets.
Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system. To address this problem, we propose a unified framework called Dynamic Curriculum Learning (DCL) to online adaptively adjust the sampling strategy and loss learning in single batch, which resulting in better generalization and discrimination. Inspired by the curriculum learning, DCL consists of two level curriculum schedulers: (1) sampling scheduler not only manages the data distribution from imbalanced to balanced but also from easy to hard; (2) loss scheduler controls the learning importance between classification and metric learning loss. Learning from these two schedulers, we demonstrate our DCL framework with the new state-of-the-art performance on the widely used face attribute dataset CelebA and pedestrian attribute dataset RAP.