论文标题
MA 3：模型不可知的对抗性增强
MA 3 : Model Agnostic Adversarial Augmentation for Few Shot learning
论文作者
论文摘要
尽管使用深层神经网络在与视觉相关的问题方面发生了进展，但在推广这些模型以表现出看不见的例子方面，仍然存在广泛的范围。在本文中，我们通过一种新颖的增强技术探索了很少的学习领域。与其他生成增强技术相比，在其中学习了输入图像的分布，我们建议学习对图像转换参数的概率分布，这些概率分布更易于学习。我们的技术是完全可区分的，可以扩展到多功能数据集和基本模型。我们在多个基本网络和2个数据集上评估了我们提出的方法，以确定该方法的鲁棒性和效率。通过添加我们的增强模块而无需改变网络体系结构，我们可以通过添加我们的增强模块来改善近4％。我们还可以使社区容易使用代码。
Despite the recent developments in vision-related problems using deep neural networks, there still remains a wide scope in the improvement of generalizing these models to unseen examples. In this paper, we explore the domain of few-shot learning with a novel augmentation technique. In contrast to other generative augmentation techniques, where the distribution over input images are learnt, we propose to learn the probability distribution over the image transformation parameters which are easier and quicker to learn. Our technique is fully differentiable which enables its extension to versatile data-sets and base models. We evaluate our proposed method on multiple base-networks and 2 data-sets to establish the robustness and efficiency of this method. We obtain an improvement of nearly 4% by adding our augmentation module without making any change in network architectures. We also make the code readily available for usage by the community.
