TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning
This addresses the challenge of incremental learning with limited data for AI systems, though it appears incremental as it builds on existing ensemble and transfer learning techniques.
The paper tackles the problem of few-shot class-incremental learning (FSCIL), where models must recognize new classes from few examples without forgetting old ones, by proposing TLCE, a transfer-learning based classifier ensemble that outperforms state-of-the-art methods in experiments on various datasets.
Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes. We propose TLCE, which ensembles multiple pre-trained models to improve separation of novel and old classes. TLCE minimizes interference between old and new classes by mapping old class images to quasi-orthogonal prototypes using episodic training. It then ensembles diverse pre-trained models to better adapt to novel classes despite data imbalance. Extensive experiments on various datasets demonstrate that our transfer learning ensemble approach outperforms state-of-the-art FSCIL methods.