Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning

25 Jun 2019  ·  Phi Vu Tran ·

Recent advances in semi-supervised learning have shown tremendous potential in overcoming a major barrier to the success of modern machine learning algorithms: access to vast amounts of human-labeled training data. Previous algorithms based on consistency regularization can harness the abundance of unlabeled data to produce impressive results on a number of semi-supervised benchmarks, approaching the performance of strong supervised baselines using only a fraction of the available labeled data. In this work, we challenge the long-standing success of consistency regularization by introducing self-supervised regularization as the basis for combining semantic feature representations from unlabeled data. We perform extensive comparative experiments to demonstrate the effectiveness of self-supervised regularization for supervised and semi-supervised image classification on SVHN, CIFAR-10, and CIFAR-100 benchmark datasets. We present two main results: (1) models augmented with self-supervised regularization significantly improve upon traditional supervised classifiers without the need for unlabeled data; (2) together with unlabeled data, our models yield semi-supervised performance competitive with, and in many cases exceeding, prior state-of-the-art consistency baselines. Lastly, our models have the practical utility of being efficiently trained end-to-end and require no additional hyper-parameters to tune for optimal performance beyond the standard set for training neural networks. Reference code and data are available at https://github.com/vuptran/sesemi

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semi-Supervised Image Classification cifar-100, 10000 Labels SESEMI SSL (ConvNet) Percentage error 38.7 # 26
Semi-Supervised Image Classification CIFAR-10, 1000 Labels SESEMI SSL (ConvNet) Accuracy 82.12 # 8
Semi-Supervised Image Classification CIFAR-10, 2000 Labels SESEMI SSL (ConvNet) Accuracy 85.78 # 4
Semi-Supervised Image Classification CIFAR-10, 4000 Labels SESEMI SSL (ConvNet) Percentage error 11.65 # 39
Semi-Supervised Image Classification SVHN, 1000 labels SESEMI SSL (ConvNet) Accuracy 94.41 # 16
Semi-Supervised Image Classification SVHN, 250 Labels SESEMI SSL (ConvNet) Accuracy 91.68 # 12
Semi-Supervised Image Classification SVHN, 500 Labels SESEMI SSL (ConvNet) Accuracy 93.5 # 6

Methods


No methods listed for this paper. Add relevant methods here