论文标题
OVA-INN：可逆神经网络的持续学习
OvA-INN: Continual Learning with Invertible Neural Networks
论文作者
论文摘要
在持续学习的领域中，目标是在一个接一个地学习几个任务，而不必从以前的任务中访问数据。已经提出了几种解决方案来解决此问题，但他们通常认为用户知道在特定样本上测试时执行的任务，或依靠以前数据中的小样本，并且大多数人一次只使用一个类别的批次仅批量，因此准确性大幅下降。在本文中，我们提出了一种新方法OVA-INN，该方法能够一次学习一个类，而无需存储任何以前的数据。为了实现这一目标，对于每个班级，我们训练一个特定的可逆神经网络来提取相关功能，以计算此类的可能性。在测试时，我们可以通过识别预测最高可能性的网络来预测样本的类别。通过这种方法，我们表明我们可以通过将可逆网络堆叠在功能提取器之上来利用验证的模型。这样，我们能够超越依靠功能学习的最先进方法来持续学习MNIST和CIFAR-100数据集。在我们的实验中，一次在训练我们的一级款会后，我们在CIFAR-100上达到了72％的精度。
In the field of Continual Learning, the objective is to learn several tasks one after the other without access to the data from previous tasks. Several solutions have been proposed to tackle this problem but they usually assume that the user knows which of the tasks to perform at test time on a particular sample, or rely on small samples from previous data and most of them suffer of a substantial drop in accuracy when updated with batches of only one class at a time. In this article, we propose a new method, OvA-INN, which is able to learn one class at a time and without storing any of the previous data. To achieve this, for each class, we train a specific Invertible Neural Network to extract the relevant features to compute the likelihood on this class. At test time, we can predict the class of a sample by identifying the network which predicted the highest likelihood. With this method, we show that we can take advantage of pretrained models by stacking an Invertible Network on top of a feature extractor. This way, we are able to outperform state-of-the-art approaches that rely on features learning for the Continual Learning of MNIST and CIFAR-100 datasets. In our experiments, we reach 72% accuracy on CIFAR-100 after training our model one class at a time.
