cs.CVNov 16, 2026

From Joint Risk to Decision Invariance: Decision-Preserving Regularization for Exemplar-Free Class-Incremental Learning

Authors: Qi Zhu, Ziang Gan, Wanting Zhang, Libao Zhang

Organizations: School of Artificial Intelligence Beijing Normal University, Beijing 100875, China

Abstract

Exemplar-free continual learning seeks to minimize joint risk over all seen tasks, yet historical data are unavailable for direct optimization. We observe that, for classification, preserving the model's decisions on previously learned classes helps retain old knowledge. This motivates Decision-Preserving Regularization (DPR). Penalizing changes in all pairwise old-class logit margins reduces algebraically to a centered relative-logit penalty. We further apply spectral whitening to remove the classifier's spectral scale bias. Because the global classifier supplies the decision constraints for the next stage, it must remain calibrated across all seen classes despite the drift of stored old-class statistics during representation updates. We therefore fit a closed-form affine map from paired current-task features to transport old-class Gaussian means and covariances into the updated feature space, then calibrate the global classifier using these distributions and current-task features. Across CIFAR-100, Tiny-ImageNet, ImageNet-Subset, and ImageNet-1K under cold-start protocols, comparisons with state-of-the-art methods show that DPR achieves higher accuracy in most settings while remaining highly efficient. Code is available at https://github.com/bnufw/dpr.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. REDAR: Reinforcement-Driven Adaptive Regularisation for Class Incremental Learning

    Oct 22, 2026Akila Ayanthi, Darshana Priyasad, Tharindu Fernando +3RL HPOClass-Incremental Learning

  2. EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning

    Mar 13, 2025Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais +2Class-Incremental LearningPrototype-Based Classification

  3. SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning

    Oct 14, 2026Teif Aldaajani, Huda Hakami, Maha A. ThafarRegularization-Based Continual LearningParameter Isolation