Dynamic Curriculum Learning for Imbalanced Data Classification release_e27zpjnb5jgvdmaf3fp3s3suvy

by Yiru Wang, Weihao Gan, Wei Wu, Junjie Yan

Released as a article .

2019  

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.
In text/plain format

Archived Files and Locations

application/pdf  1.6 MB
file_lw7fncnqcrh5bhyrvhl4svejk4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-01-21
Version   v1
Language   en ?
arXiv  1901.06783v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 46775389-d48d-4b26-be42-6ecd37c092a8
API URL: JSON