Dynamic Curriculum Learning for Imbalanced Data Classification
Preprint
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.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images2018
- HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis2017
- Class Rectification Hard Mining for Imbalanced Deep Learning2017
- Attribute Recognition by Joint Recurrent Learning of Context and Correlation2017
- Multi-Modal Curriculum Learning for Semi-Supervised Image ClassificationIEEE Transactions on Image Processing, 2016
- ODOC-ELM: Optimal decision outputs compensation-based extreme learning machine for classifying imbalanced dataKnowledge-Based Systems, 2016
- A dynamic over-sampling procedure based on sensitivity for multi-class problemsPattern Recognition, 2011
- Supervised Neural Network Modeling: An Empirical Investigation Into Learning From Imbalanced Data With Labeling ErrorsIEEE Transactions on Neural Networks, 2010
- Decision threshold adjustment in class predictionSAR and QSAR in Environmental Research, 2006
- Training cost-sensitive neural networks with methods addressing the class imbalance problemIEEE Transactions on Knowledge and Data Engineering, 2005