面向元学习的自适应任务采样
Adaptive Task Sampling for Meta-Learning
摘要：
元学习方法在计算机视觉中得到了广泛的研究和应用，特别是对于Few-Shot分类任务。用于Few-Shot分类的元学习的关键思想是通过在Meta训练数据中随机采样类来构造用于情景训练的Few-Shot任务，以模拟测试时面临的Few-Shot情况。虽然丰富的工作线只关注如何跨任务提取元知识，但我们利用了如何生成信息任务的补充问题。我们认为，随机抽样的任务可能是次优的和无信息的（例如，将“狗”与“膝上型计算机”分类的任务通常是微不足道的）。在本文中，我们提出了一个自适应的任务采样方法，以提高泛化性能。与基于实例的采样不同，基于任务的采样更具挑战性，因为每个事件中任务的隐含定义。因此，我们相应地提出了一种基于贪婪类对的抽样方法，该方法根据类对潜力选择困难的任务。我们在两个Few-Shot分类基准上评估了我们的自适应任务采样方法，它在不同的特征骨干，Meta学习算法和数据集上实现了一致的改进。
英文摘要：
Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks. The key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time by randomly sampling classes in meta-training data to construct few-shot tasks for episodic training. While a rich line of work focuses solely on how to extract meta-knowledge across tasks, we exploit the complementary problem on how to generate informative tasks. We argue that the randomly sampled tasks could be sub-optimal and uninformative (e.g., the task of classifying "dog" from "laptop" is often trivial) to the meta-learner. In this paper, we propose an adaptive task sampling method to improve the generalization performance. Unlike instance based sampling, task based sampling is much more challenging due to the implicit definition of the task in each episode. Therefore, we accordingly propose a greedy class-pair based sampling method, which selects difficult tasks according to class-pair potentials. We evaluate our adaptive task sampling method on two few-shot classification benchmarks, and it achieves consistent improvements across different feature backbones, meta-learning algorithms and datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
