2026
AdaPrior: Bayesian-Inspired Adaptive Prior Correction for Long-Tailed Continual Learning
CVPR 2026
Long-Tail Class Incremental Learning (LTCIL) combines two fundamental challenges: catastrophic forgetting of past tasks and severe class imbalance. Existing approaches mitigate one challenge at a time, through rehearsal, reweighting, or classifier alignment, but they typically assume static priors a