Learning Muti-expert Distribution Calibration for Long-tailed Video Classification

TL;DR

This paper introduces a multi-expert distribution calibration approach for long-tailed video classification, effectively addressing class imbalance by modeling intra- and inter-class distributions, leading to improved performance on imbalanced datasets.

Contribution

It proposes an end-to-end method that leverages two-level distribution information to enhance long-tailed video classification, a novel extension from image to video data.

Findings

Achieves state-of-the-art results on long-tailed video datasets.

Effectively balances performance between head and tail classes.

Demonstrates significant improvement over existing methods.

Abstract

Most existing state-of-the-art video classification methods assume that the training data obey a uniform distribution. However, video data in the real world typically exhibit an imbalanced long-tailed class distribution, resulting in a model bias towards head class and relatively low performance on tail class. While the current long-tailed classification methods usually focus on image classification, adapting it to video data is not a trivial extension. We propose an end-to-end multi-expert distribution calibration method to address these challenges based on two-level distribution information. The method jointly considers the distribution of samples in each class (intra-class distribution) and the overall distribution of diverse data (inter-class distribution) to solve the issue of imbalanced data under long-tailed distribution. By modeling the two-level distribution information, the model can jointly consider the head classes and the tail classes and significantly transfer the knowledge from the head classes to improve the performance of the tail classes. Extensive experiments verify that our method achieves state-of-the-art performance on the long-tailed video classification task.