Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks
This work addresses the challenge of improving image classification accuracy in semi-supervised settings with scarce labeled data, offering an incremental advancement by combining FF-CNNs with data selection and ensemble methods.
The paper tackles the problem of semi-supervised image classification by proposing a framework using feedforward-designed convolutional neural networks (FF-CNNs) that avoid backpropagation, and it shows that this solution outperforms backpropagation-based CNNs when labeled data is limited, with ensemble systems achieving further accuracy gains on MNIST, SVHN, and CIFAR-10 datasets.
A semi-supervised learning framework using the feedforward-designed convolutional neural networks (FF-CNNs) is proposed for image classification in this work. One unique property of FF-CNNs is that no backpropagation is used in model parameters determination. Since unlabeled data may not always enhance semi-supervised learning, we define an effective quality score and use it to select a subset of unlabeled data in the training process. We conduct experiments on the MNIST, SVHN, and CIFAR-10 datasets, and show that the proposed semi-supervised FF-CNN solution outperforms the CNN trained by backpropagation (BP-CNN) when the amount of labeled data is reduced. Furthermore, we develop an ensemble system that combines the output decision vectors of different semi-supervised FF-CNNs to boost classification accuracy. The ensemble systems can achieve further performance gains on all three benchmarking datasets.