papers AI Learner
The Github is limit! Click to go to the new site.

Dynamic Curriculum Learning for Imbalanced Data Classification

2019-01-21
Yiru Wang, Weihao Gan, Wei Wu, Junjie Yan

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.06783

PDF

http://arxiv.org/pdf/1901.06783


Similar Posts

Comments