Towards Realistic Class-Incremental Learning with Free-Flow Increments
This addresses a practical limitation in CIL systems for real-world applications where data streams are unpredictable, though it is incremental as it builds on existing CIL methods.
The paper tackles the problem of class-incremental learning (CIL) under realistic conditions where new classes arrive in variable numbers, formalized as Free-Flow Class-Incremental Learning (FFCIL), and proposes a model-agnostic framework that stabilizes learning and improves robustness, yielding consistent performance gains across baselines.
Class-incremental learning (CIL) is typically evaluated under predefined schedules with equal-sized tasks, leaving more 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 more 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. We propose a model-agnostic framework for robust CIL learning under free-flow arrivals. It comprises a class-wise mean (CWM) objective that replaces sample frequency weighted loss with uniformly aggregated class-conditional supervision, thereby stabilizing the learning signal across free-flow class increments, as well as method-wise adjustments that improve robustness for representative CIL paradigms. Specifically, we constrain distillation to replayed data, normalize the scale of contrastive and knowledge transfer losses, and introduce Dynamic Intervention Weight Alignment (DIWA) to prevent over-adjustment caused by unstable statistics from small class increments. Experiments confirm a clear performance degradation across various CIL baselines under FFCIL, while our strategies yield consistent gains.