Towards Realistic Class-Incremental Learning with Free-Flow Increments

ArXi:2604.02765v1 Announce Type: new Class-incremental learning (CIL) is typically evaluated under predefined schedules with equal-sized tasks, leaving realistic and complex cases unexplored. However, a practical CIL system should learns immediately when any number of new classes arrive, without forcing fixed-size tasks. We formalize this setting as Free-Flow Class-Incremental Learning (FFCIL), where data arrives as a realistic stream with a highly variable number of unseen classes each step. It will make many existing CIL methods brittle and lead to clear performance degradation.