论文标题
元数据的进步：AAAI 2021挑战和研讨会
Advances in MetaDL: AAAI 2021 challenge and workshop
论文作者
论文摘要
为了刺激使用深度学习技术（MetAdl）的金属性进步，我们在2021年组织了一个挑战和相关的研讨会。本文介绍了挑战及其结果的设计，并总结了研讨会上的演讲。挑战的重点是小图像的几个学习分类任务。在严格的计算限制下，参与者的代码提交以统一的方式进行。这给解决方案设计带来了压力，以使用现有的体系结构骨干和/或预训练的网络。获胜方法的特征是在第二个流行的CNN骨架的最后一层培训的各种分类器中，在元训练数据（不一定以情节方式）上进行了罚款，然后在标记的支持下进行了培训，并在未标记的Meta测试数据的未标记的查询集上进行了测试。
To stimulate advances in metalearning using deep learning techniques (MetaDL), we organized in 2021 a challenge and an associated workshop. This paper presents the design of the challenge and its results, and summarizes presentations made at the workshop. The challenge focused on few-shot learning classification tasks of small images. Participants' code submissions were run in a uniform manner, under tight computational constraints. This put pressure on solution designs to use existing architecture backbones and/or pre-trained networks. Winning methods featured various classifiers trained on top of the second last layer of popular CNN backbones, fined-tuned on the meta-training data (not necessarily in an episodic manner), then trained on the labeled support and tested on the unlabeled query sets of the meta-test data.
