arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.09151cs.LGcs.CV
收藏

几何约束下的少样本学习

Few-Shot Learning with Geometric Constraints

Korea University(高丽大学)

Hong-Gyu Jung, Seong-Whan Lee

摘要:

在这篇文章中,我们考虑了分类的少样本学习问题。我们假设一个网络是用大量的训练样本训练的,我们的目标是向它添加只有几个的新类别,例如,一个或五个训练样本。这是一个具有挑战性的场景,因为:1)在基础类别和新类别中都需要高性能; 2)用几个训练样本训练新类别的网络可能会污染为基础类别训练得很好的特征空间。为了解决这些挑战,我们提出了两个几何约束,微调网络与一些训练样本。第一个约束使新类别的特征能够聚集在类别权重附近,第二个约束使新类别的权重远离基本类别的权重。通过应用所提出的约束,我们提取新类别的判别特征,同时保留为基本类别学习的特征空间。使用公共数据集进行少样本学习,这些数据集是ImageNet的子集,我们证明了所提出的方法大大优于流行的方法。

英文摘要:

In this article, we consider the problem of few-shot learning for classification. We assume a network trained for base categories with a large number of training examples, and we aim to add novel categories to it that have only a few, e.g., one or five, training examples. This is a challenging scenario because: 1) high performance is required in both the base and novel categories; and 2) training the network for the new categories with a few training examples can contaminate the feature space trained well for the base categories. To address these challenges, we propose two geometric constraints to fine-tune the network with a few training examples. The first constraint enables features of the novel categories to cluster near the category weights, and the second maintains the weights of the novel categories far from the weights of the base categories. By applying the proposed constraints, we extract discriminative features for the novel categories while preserving the feature space learned for the base categories. Using public data sets for few-shot learning that are subsets of ImageNet, we demonstrate that the proposed method outperforms prevalent methods by a large margin.

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。

↑