Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks

TL;DR

This paper introduces a semi-supervised learning method using feedforward-designed CNNs that do not rely on backpropagation, effectively utilizing unlabeled data and ensemble techniques to improve image classification accuracy.

Contribution

The work presents a novel semi-supervised FF-CNN framework that avoids backpropagation and employs data quality scoring and ensemble methods for enhanced performance.

Findings

Outperforms backpropagation-trained CNNs with limited labeled data

Effective unlabeled data selection improves semi-supervised learning

Ensemble systems further boost classification accuracy

Abstract

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.