AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
Keeping AI from forgetting old categories when learning new ones
When AI systems learn new object categories over time, they typically forget what they learned before—a problem called catastrophic forgetting. This paper shows how to break down the recognition process into two separate steps (extracting distinguishing features and combining them) and stabilize each one independently, allowing models to learn continuously without losing old knowledge. The method outperforms existing approaches on standard benchmarks.
Real-world AI systems need to learn new categories throughout their lifespan without being retrained from scratch each time. Current approaches either require keeping all old training data (expensive and often impossible) or suffer severe accuracy drops on previously learned categories. This work enables practical continual learning systems that maintain performance on old tasks while successfully absorbing new ones.