DeepAI AI Chat
Log In Sign Up

Dynamic Curriculum Learning for Imbalanced Data Classification

by   Yiru Wang, et al.
SenseTime Corporation

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.


page 1

page 2

page 3

page 4


Class Rectification Hard Mining for Imbalanced Deep Learning

Recognising detailed facial or clothing attributes in images of people i...

Improving Imbalanced Text Classification with Dynamic Curriculum Learning

Recent advances in pre-trained language models have improved the perform...

Mixed-order self-paced curriculum learning for universal lesion detection

Self-paced curriculum learning (SCL) has demonstrated its great potentia...

HuCurl: Human-induced Curriculum Discovery

We introduce the problem of curriculum discovery and describe a curricul...

Curriculum Learning with Diversity for Supervised Computer Vision Tasks

Curriculum learning techniques are a viable solution for improving the a...

A step towards understanding why classification helps regression

A number of computer vision deep regression approaches report improved r...

Curriculum Learning of Visual Attribute Clusters for Multi-Task Classification

Visual attributes, from simple objects (e.g., backpacks, hats) to soft-b...