cs.LGJun 23, 2023

A Theoretical Bridge Between Long-Tailed Recognition and Continual Learning

Authors: Mahdiyar Molahasani, Michael Greenspan, Ali Etemad

Organizations: Department of Electrical and Computer Engineering & Ingenuity Labs Research Institute, Queen’s University, Kingston, Canada

Abstract

We theoretically and empirically establish a previously unexplored connection between Long-Tailed Recognition (LTR) and Continual Learning (CL). Specifically, we show that training on a long-tailed dataset with imbalance factor IF\mathrm{IF} drives model parameters into an O(1/IF)O(1/\sqrt{\mathrm{IF}}) neighborhood of the dominant-class solution, under both uniform and exponentially decaying cardinality distributions. Building on this result, we establish an objective-level reformulation of LTR as a sequential learning problem and prove that the CL objective upper-bounds the balanced LTR loss up to a constant determined by the residual Head loss. Motivated by this connection, we introduce Continual Learning for Long-Tailed Recognition (CLTR), a principled framework that leverages standard off-the-shelf CL methods to sequentially learn Head and Tail classes while mitigating catastrophic forgetting. Extensive experiments on CIFAR100-LT, CIFAR10-LT, ImageNet-LT, and Caltech256 validate our theoretical predictions and demonstrate strong performance across diverse LTR benchmarks. In the foundation-model regime, CLTR with DualPrompt on a CLIP backbone outperforms standard adaptation baselines and is competitive with specialized methods using external semantic supervision. Our work bridges LTR and CL both theoretically and empirically, providing a principled approach for addressing long-tailed learning using standard CL strategies.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Reframing Long-Tailed Learning via Loss Landscape Geometry

    Mar 22, 2026Shenghan Chen, Yiming Liu, Yanzhen Wang +2Long-Tail LearningLoss Landscape Geometry

  2. VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition

    Sep 4, 2026Jiangang Zhu, Zheng Wang, Bin Zhu +2Long-Tailed ClassificationEnsemble Learning

  3. Dynamic Distillation and Gradient Consistency for Robust Long-Tailed Incremental Learning

    May 5, 2026Taigo Sakai, Kazuhiro HottaClass-Incremental LearningLong-Tail Learning