DeepAI AI Chat
Log In Sign Up

Mining Minority-class Examples With Uncertainty Estimates

by   Gursimran Singh, et al.
HUAWEI Technologies Co., Ltd.
Simon Fraser University
McMaster University

In the real world, the frequency of occurrence of objects is naturally skewed forming long-tail class distributions, which results in poor performance on the statistically rare classes. A promising solution is to mine tail-class examples to balance the training dataset. However, mining tail-class examples is a very challenging task. For instance, most of the otherwise successful uncertainty-based mining approaches struggle due to distortion of class probabilities resulting from skewness in data. In this work, we propose an effective, yet simple, approach to overcome these challenges. Our framework enhances the subdued tail-class activations and, thereafter, uses a one-class data-centric approach to effectively identify tail-class examples. We carry out an exhaustive evaluation of our framework on three datasets spanning over two computer vision tasks. Substantial improvements in the minority-class mining and fine-tuned model's performance strongly corroborate the value of our proposed solution.


page 1

page 2

page 3

page 4


Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining

Continued improvements in deep learning architectures have steadily adva...

Long-tail Recognition via Compositional Knowledge Transfer

In this work, we introduce a novel strategy for long-tail recognition th...

Repeated out of Sample Fusion in the Estimation of Small Tail Probabilities

In pursuit of a small tail probability p, it is shown how to construct b...

Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data

Classification on long-tailed distributed data is a challenging problem,...

A Study on Action Detection in the Wild

The recent introduction of the AVA dataset for action detection has caus...

Learning to Segment the Tail

Real-world visual recognition requires handling the extreme sample imbal...

Taming the Long Tail of Deep Probabilistic Forecasting

Deep probabilistic forecasting is gaining attention in numerous applicat...