论文标题
几乎没有几何限制的学习
Few-Shot Learning with Geometric Constraints
论文作者
论文摘要
在本文中，我们考虑了几乎没有用于分类的学习问题。我们假设一个网络对基本类别进行了培训，其中有大量的培训示例，我们的目标是将新颖的类别添加到其中只有少数，例如一个或五个培训示例。这是一个具有挑战性的场景，因为：1）在基础和新颖类别中都需要高性能； 2）通过一些培训示例为新类别培训网络可能会污染对基本类别训练的功能空间。为了应对这些挑战，我们提出了两个几何约束，以一些培训示例微调网络。第一个约束使新类别的特征可以聚集在类别权重附近，而第二个则保持了远离基本类别权重的新颖类别的权重。通过应用提出的约束，我们为新型类别提取歧视性特征，同时保留为基本类别学习的特征空间。使用公共数据集作为ImageNet的子集进行几次学习，我们证明了所提出的方法的表现要优于普遍的方法。
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.
