CAMP: Coupled Alignment of Manifold and Prototypes for Exemplar-Free Class-Incremental Learning

Exemplar-free class-incremental learning (EFCIL) requires sequentially learning new classes without storing past data, a setting where catastrophic forgetting stems from the progressive drift of feature representations across tasks. Existing methods treat feature drift and classifier misalignment as separate concerns, applying knowledge distillation to constrain the backbone and post-hoc compensation to correct prototypes, without a unified understanding of how these two processes interact. We show that they are in fact two sides of the same geometric problem: the linear classifier defines a pullback metric on the feature manifold, so manifold stability is a prerequisite for valid metric recalibration, and the two must be addressed as a single coupled system rather than as independent stages. We propose CAMP ($\underline{C}$oupled $\underline{A}$lignment of $\underline{M}$anifold and $\underline{P}$rototypes), a framework where these two processes are interlocked as a causal pipeline rather than stacked as independent modules. CAMP consists of $\underline{F}$eature $\underline{M}$anifold $\underline{C}$onstraint (FMC), which provides a gradient-complete manifold constraint during training, $\underline{K}$ernel $\underline{S}$hift $\underline{C}$ompensation (KSC), which corrects residual drift via a non-parametric minimax-optimal estimator, and $\underline{P}$rototype-$\underline{A}$nchored $\underline{C}$lassifier $\underline{R}$ecalibration (PACR), which re-anchors drifted classifier weights to corrected prototypes, together forming a single causal chain. Experiments on multiple benchmarks demonstrate state-of-the-art performance with superior retention, showing that these two problems are best solved as a coupled system rather than in isolation.