Continual Few-Shot Learning Using HyperTransformers

arXiv (Cornell University)(2023)

引用 0|浏览19
暂无评分
摘要
We focus on the problem of learning without forgetting from multiple tasks arriving sequentially, where each task is defined using a few-shot episode of novel or already seen classes. We approach this problem using the recently published HyperTransformer (HT), a Transformer-based hypernetwork that generates specialized task-specific CNN weights directly from the support set. In order to learn from a continual sequence of tasks, we propose to recursively re-use the generated weights as input to the HT for the next task. This way, the generated CNN weights themselves act as a representation of previously learned tasks, and the HT is trained to update these weights so that the new task can be learned without forgetting past tasks. This approach is different from most continual learning algorithms that typically rely on using replay buffers, weight regularization or task-dependent architectural changes. We demonstrate that our proposed Continual HyperTransformer method equipped with a prototypical loss is capable of learning and retaining knowledge about past tasks for a variety of scenarios, including learning from mini-batches, and task-incremental and class-incremental learning scenarios.
更多
查看译文
关键词
learning,few-shot
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要