Few-Shot Incremental Learning Using HyperTransformers

ICLR 2023(2023)

引用 0|浏览53
Incremental few-shot learning methods make it possible to learn without forgetting from multiple few-shot tasks arriving sequentially. In this work we approach this problem using the recently published HyperTransformer (HT): a hypernetwork that generates task-specific CNN weights directly from the support set. We propose to re-use these generated weights as an input to the HT for the next task of the continual-learning sequence. Thus, the HT uses the weights themselves as the representation of the previously learned tasks. This approach is different from most continual learning algorithms that typically rely on using replay buffers, weight regularization or task-dependent architectural changes. Instead, we show that the HT works akin to a recurrent model, relying on the weights from the previous task and a support set from a new task. We demonstrate that a single HT equipped with a prototypical loss is capable of learning and retaining knowledge about past tasks for two continual learning scenarios: incremental-task learning and incremental-class learning.
few-shot learning,incremental learning,continual learning,transformers,hypernetworks
AI 理解论文
Chat Paper