Few-Shot Incremental Learning Using HyperTransformers

Max Vladymyrov, Andrey Zhmoginov, Mark Sandler

Keywords: few-shot learning, incremental learning, continual learning, transformers, hypernetworks

Abstract: 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.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

TL;DR: An attention-based recurrent hypernetwork for incremental few-shot learning using prototypical loss