SOURCE-LINKED INTELLIGENCE

Mini-batch Sampling Strategies for Long-Tailed Image Classification: An Empirical Study on CIFAR-100-LT

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Real-world datasets often exhibit long-tailed class distributions, where a few head classes contain a large number of training samples while a large number of tail classes have only a few. The composition of each mini-batch, determined by the sampling strategy, governs which classes contribute to the stochastic gradient estimate, and therefore affects convergence behaviour and generalisation across the whole class spectrum. We provide a systematic theoretical and empirical comparison of four mini-batch sampling strategies for long-tailed image classification: uniform instance sampling, class-b

Read original source ↗ Open in workspace

recordType

paper

region

Global