AlphaNet: Improving Long-Tail Classification By Combining Classifiers

TL;DR

AlphaNet is a post hoc correction method that enhances rare class accuracy in long-tail classification by combining classifiers of similar frequent classes, with minimal impact on overall accuracy.

Contribution

It introduces a novel post hoc approach to improve rare class performance by linearly combining classifiers of similar frequent classes, applicable to existing models.

Findings

Significantly improves rare class accuracy across multiple datasets.

Maintains overall accuracy with minimal changes.

Provides a controllable trade-off between rare and overall accuracy.

Abstract

Methods in long-tail learning focus on improving performance for data-poor (rare) classes; however, performance for such classes remains much lower than performance for more data-rich (frequent) classes. Analyzing the predictions of long-tail methods for rare classes reveals that a large number of errors are due to misclassification of rare items as visually similar frequent classes. To address this problem, we introduce AlphaNet, a method that can be applied to existing models, performing post hoc correction on classifiers of rare classes. Starting with a pre-trained model, we find frequent classes that are closest to rare classes in the model's representation space and learn weights to update rare class classifiers with a linear combination of frequent class classifiers. AlphaNet, applied to several models, greatly improves test accuracy for rare classes in multiple long-tailed datasets, with very little change to overall accuracy. Our method also provides a way to control the trade-off between rare class and overall accuracy, making it practical for long-tail classification in the wild.