Few-shot object detection aims to simultaneously localize and classify the objects in an image with limited training samples. However, most existing few-shot object detection methods focus on extracting the features of a few samples of novel classes that lack diversity. Hence, they may not be sufficient to capture the data distribution. To address that limitation, in this paper, we propose a novel approach in which we train a generator to generate synthetic data for novel classes. Still, directly training a generator on the novel class is not effective due to the lack of novel data. To overcome that issue, we leverage the large-scale dataset of base classes. Our overarching goal is to train a generator that captures the data variations of the base dataset. We then transform the captured variations into novel classes by generating synthetic data with the trained generator. To encourage the generator to capture data variations on base classes, we propose to train the generator with an optimal transport loss that minimizes the optimal transport distance between the distributions of real and synthetic data. Extensive experiments on two benchmark datasets demonstrate that the proposed method outperforms the state of the art. Source code will be available.

翻译：小样本目标检测旨在利用有限的训练样本同时定位和分类图像中的目标。然而，现有的大多数小样本目标检测方法侧重于提取少数新类样本的特征，这些样本缺乏多样性，因此可能不足以捕捉数据分布。为解决这一限制，本文提出了一种新方法，即训练一个生成器为新型类别生成合成数据。然而，由于新型数据缺乏，直接在新型类上训练生成器效果不佳。为解决这一问题，我们利用基类的大规模数据集。我们的总体目标是训练一个能够捕捉基类数据变化的生成器，然后通过该生成器生成合成数据，将捕捉到的变化迁移到新型类中。为鼓励生成器捕捉基类的数据变化，我们提出使用最优传输损失训练生成器，该损失最小化真实数据与合成数据分布之间的最优传输距离。在两个基准数据集上的大量实验表明，所提方法优于现有最先进方法。源代码将公开。