SLARC: Shrinkage-Controlled Low-Rank Alignment and Regularized Classification for Exemplar-Free Class-Incremental Learning

Continued adaptation of pre-trained representations can make stored class statistics stale. In exemplar-free class-incremental learning, old images are unavailable for recomputing these statistics. While existing methods compensate for representation drift and exploit class covariances for classification, two questions remain challenging without old images: how much of an estimated correction should be applied to old-class means, and how much class-specific covariance structure should the classifier retain? Shrinkage-Controlled Low-Rank Alignment and Regularized Classification (SLARC) addresses these questions through constrained mean alignment and a regularized Gaussian head. The alignment fits a low-rank affine residual and reduces its strength when disagreement between image-split fits is large relative to the proposed movement at old-class means. The head uses maintained means and combines retained class covariances with pooled and spherical estimates. Scores recorded at class introduction select the regularization parameters, allowing earlier classes to inform the choice without retaining their images or individual features. Across four ten-task benchmarks, SLARC improves E${}^2$-LoRA's final accuracy by $0.70$–$4.08$ percentage points.