Temporal Ensembling for Semi-Supervised Learning

TL;DR

This paper introduces a self-ensembling method for semi-supervised learning that leverages ensemble predictions across epochs and augmentations, significantly improving accuracy on standard benchmarks with limited labeled data.

Contribution

The paper proposes a novel self-ensembling approach for semi-supervised learning that enhances label prediction and achieves state-of-the-art results on benchmark datasets.

Findings

Reduced error rate on SVHN from 18.44% to 7.05%.

Lowered error rate on CIFAR-10 from 18.63% to 16.55%.

Improved CIFAR-100 accuracy using unlabeled data.

Abstract

In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus prediction of the unknown labels using the outputs of the network-in-training on different epochs, and most importantly, under different regularization and input augmentation conditions. This ensemble prediction can be expected to be a better predictor for the unknown labels than the output of the network at the most recent training epoch, and can thus be used as a target for training. Using our method, we set new records for two standard semi-supervised learning benchmarks, reducing the (non-augmented) classification error rate from 18.44% to 7.05% in SVHN with 500 labels and from 18.63% to 16.55% in CIFAR-10 with 4000 labels, and further to 5.12% and 12.16% by enabling the standard augmentations. We additionally obtain a clear improvement in CIFAR-100 classification accuracy by using random images from the Tiny Images dataset as unlabeled extra inputs during training. Finally, we demonstrate good tolerance to incorrect labels.