Anchor the Past, Calibrate the Present: Maintaining Geometric Consistency for Online Class-Incremental Learning

Realistic open environments demand continual recognition of emerging and previously learned categories, motivating online class-incremental learning (OCIL). As pretrained models (PTMs) adapt to new classes, old-class features can drift from historical classifier directions, while the classifier can become misaligned with the updated feature space. Replaying old examples alone does not maintain geometric consistency across these updates. To bridge this gap, we propose Anchoring in Replay (AIR), which contains two complementary parts. Historical geometry anchoring (HGA) aligns old-class replay features with fixed directions from the previous calibrated classifier, while mixed-geometry calibration (MGC) recalibrates the classifier from memory prototypes in the updated feature space. The calibrated directions support current prediction and anchor the next task. Under OCIL protocol, AIR achieves the best final average accuracy (FAA) among the evaluated replay-based methods on four benchmarks across three replay budgets.