A Unified Framework with Meta-dropout for Few-shot Learning
This work addresses the challenge of training deep neural networks with limited annotated data, which is a common problem in machine learning, but it appears incremental as it builds on existing meta-learning approaches.
The paper tackles the problem of few-shot learning by proposing a unified meta-learning framework and a meta-dropout strategy to improve generalization, achieving validated effectiveness on datasets like Pascal VOC, MS COCO, CUB, and mini-ImageNet.
Conventional training of deep neural networks usually requires a substantial amount of data with expensive human annotations. In this paper, we utilize the idea of meta-learning to explain two very different streams of few-shot learning, i.e., the episodic meta-learning-based and pre-train finetune-based few-shot learning, and form a unified meta-learning framework. In order to improve the generalization power of our framework, we propose a simple yet effective strategy named meta-dropout, which is applied to the transferable knowledge generalized from base categories to novel categories. The proposed strategy can effectively prevent neural units from co-adapting excessively in the meta-training stage. Extensive experiments on the few-shot object detection and few-shot image classification datasets, i.e., Pascal VOC, MS COCO, CUB, and mini-ImageNet, validate the effectiveness of our method.