Abstract
Given an initial recognition model already trained on a set of base classes, the goal of this work is to develop a meta-model for few-shot learning. The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new model that can correctly classify in a unified way both the novel and the base classes. To accomplish this goal it must learn to output the appropriate classification weight vectors for those two types of classes. To build our meta-model we make use of two main innovations: we propose the use of a Denoising Autoencoder network (DAE) that (during training) takes as input a set of classification weights corrupted with Gaussian noise and learns to reconstruct the target-discriminative classification weights. In this case, the injected noise on the classification weights serves the role of regularizing the weight generating meta-model. Furthermore, in order to capture the co-dependencies between different classes in a given task instance of our meta-model, we propose to implement the DAE model as a Graph Neural Network (GNN). In order to verify the efficacy of our approach, we extensively evaluate it on ImageNet based few-shot benchmarks and we report strong results that surpass prior approaches. The code and models of our paper will be published on: https://github.com/gidariss/wDAE_GNN_FewShot
Abstract (translated)
给定一个已经在一组基础类上训练过的初始识别模型,本工作的目标是开发一个用于少镜头学习的元模型。元模型作为一个新的类输入,每个类只需很少的训练实例,必须适当地将现有的识别模型转化为一个新的模型,该模型能够对新类和基础类进行统一的正确分类。为了实现这个目标,它必须学习为这两种类型的类输出适当的分类权重向量。为了建立元模型,我们利用了两个主要的创新点:我们提出了一种去噪自动编码器网络(dae),该网络(在训练期间)将一组受高斯噪声影响的分类权重作为输入,并学习重建目标识别分类权重。在这种情况下,分类权重上的注入噪声起到了调整权重生成元模型的作用。此外,为了在元模型的一个给定任务实例中捕获不同类之间的相互依赖关系,我们建议将该模型作为一个图形神经网络(GNN)来实现。为了验证我们的方法的有效性,我们在基于图像网的少数镜头基准上对其进行了广泛的评估,并且我们报告了超过先前方法的强大结果。本文的代码和模型将发表在:https://github.com/gidaris/wdae_gnn_fewshot
URL
https://arxiv.org/abs/1905.01102