Class-Balanced Loss Based on Effective Number of Samples

TLDR

Long‑tailed data distributions, where a few classes dominate and many are under‑represented, pose a critical challenge for large‑scale real‑world datasets. The authors contend that the marginal benefit of adding more samples diminishes as the sample size grows. They propose measuring an effective number of samples by assigning each point a small neighboring volume, yielding the formula \((1-\beta^n)/(1-\beta)\), and use this to re‑weight the loss, creating a class‑balanced loss evaluated on CIFAR, ImageNet, and iNaturalist. Experiments demonstrate that training with this class‑balanced loss yields significant performance improvements on long‑tailed datasets.

Abstract

With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). Existing solutions typically adopt class re-balancing strategies such as re-sampling and re-weighting based on the number of observations for each class. In this work, we argue that as the number of samples increases, the additional benefit of a newly added data point will diminish. We introduce a novel theoretical framework to measure data overlap by associating with each sample a small neighboring region rather than a single point. The effective number of samples is defined as the volume of samples and can be calculated by a simple formula $(1-\beta^{n})/(1-\beta)$, where $n$ is the number of samples and $\beta \in [0,1)$ is a hyperparameter. We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss. Comprehensive experiments are conducted on artificially induced long-tailed CIFAR datasets and large-scale datasets including ImageNet and iNaturalist. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve significant performance gains on long-tailed datasets.