TACLE: Task and Class-aware Exemplar-free Semi-supervised Class Incremental Learning
This addresses a challenging incremental learning scenario for AI systems that need to continuously adapt to new classes with minimal supervision, though it appears incremental as it builds on pre-trained models and existing techniques.
The paper tackles the problem of exemplar-free semi-supervised class incremental learning, where models learn new classes from limited labeled and unlabeled data without access to past exemplars, and demonstrates effectiveness on benchmark datasets like CIFAR10, CIFAR100, and ImageNet-Subset100, including in imbalanced and extreme cases like one labeled example per class.
We propose a novel TACLE (TAsk and CLass-awarE) framework to address the relatively unexplored and challenging problem of exemplar-free semi-supervised class incremental learning. In this scenario, at each new task, the model has to learn new classes from both (few) labeled and unlabeled data without access to exemplars from previous classes. In addition to leveraging the capabilities of pre-trained models, TACLE proposes a novel task-adaptive threshold, thereby maximizing the utilization of the available unlabeled data as incremental learning progresses. Additionally, to enhance the performance of the under-represented classes within each task, we propose a class-aware weighted cross-entropy loss. We also exploit the unlabeled data for classifier alignment, which further enhances the model performance. Extensive experiments on benchmark datasets, namely CIFAR10, CIFAR100, and ImageNet-Subset100 demonstrate the effectiveness of the proposed TACLE framework. We further showcase its effectiveness when the unlabeled data is imbalanced and also for the extreme case of one labeled example per class.