Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting
This addresses the problem of few-shot learning for AI systems that need to continuously learn new classes without forgetting old ones, representing an incremental improvement over existing methods.
The paper tackles the challenges of learning novel classes from few samples while preventing forgetting of base classes and achieving classifier calibration across all classes, achieving state-of-the-art results on four benchmark datasets for image and video few-shot classification.
Both generalized and incremental few-shot learning have to deal with three major challenges: learning novel classes from only few samples per class, preventing catastrophic forgetting of base classes, and classifier calibration across novel and base classes. In this work we propose a three-stage framework that allows to explicitly and effectively address these challenges. While the first phase learns base classes with many samples, the second phase learns a calibrated classifier for novel classes from few samples while also preventing catastrophic forgetting. In the final phase, calibration is achieved across all classes. We evaluate the proposed framework on four challenging benchmark datasets for image and video few-shot classification and obtain state-of-the-art results for both generalized and incremental few shot learning.