论文标题
跨域进行元元学习
Cross-Domain Few-Shot Learning with Meta Fine-Tuning
论文作者
论文摘要
在本文中，我们解决了CVPR 2020 Challenge提出的新的跨域少数学习基准。为此，我们以域适应性的最新方法为基础，并且很少学习，以创建一个可以培训以执行这两个任务的系统。受到创建旨在微调模型的需求的启发，我们探索了转移学习（微调）与元学习算法的集成，以训练具有特定层的网络，该网络旨在在后来的微型调查阶段进行调整。为此，我们修改了情节训练过程，以包括一阶MAML基于MAML的元学习算法，并使用图形神经网络模型作为随后的元学习模块。我们发现我们提出的方法有助于显着提高准确性，尤其是在与数据增强结合使用时。在我们的最终结果中，我们将新方法与基线方法结合在简单的集合中，并在基准上获得73.78％的平均精度。这比仅在迷你胶原上接受培训的现有基准有6.51％的改善。
In this paper, we tackle the new Cross-Domain Few-Shot Learning benchmark proposed by the CVPR 2020 Challenge. To this end, we build upon state-of-the-art methods in domain adaptation and few-shot learning to create a system that can be trained to perform both tasks. Inspired by the need to create models designed to be fine-tuned, we explore the integration of transfer-learning (fine-tuning) with meta-learning algorithms, to train a network that has specific layers that are designed to be adapted at a later fine-tuning stage. To do so, we modify the episodic training process to include a first-order MAML-based meta-learning algorithm, and use a Graph Neural Network model as the subsequent meta-learning module. We find that our proposed method helps to boost accuracy significantly, especially when combined with data augmentation. In our final results, we combine the novel method with the baseline method in a simple ensemble, and achieve an average accuracy of 73.78% on the benchmark. This is a 6.51% improvement over existing benchmarks that were trained solely on miniImagenet.
