Milking CowMask for Semi-Supervised Image Classification

03/26/2020
by   Geoff French, et al.
4

Consistency regularization is a technique for semi-supervised learning that has recently been shown to yield strong results for classification with few labeled data. The method works by perturbing input data using augmentation or adversarial examples, and encouraging the learned model to be robust to these perturbations on unlabeled data. Here, we evaluate the use of a recently proposed augmentation method, called CowMasK, for this purpose. Using CowMask as the augmentation method in semi-supervised consistency regularization, we establish a new state-of-the-art result on Imagenet with 10 a top-5 error of 8.76 method that is much simpler than alternative methods. We further investigate the behavior of CowMask for semi-supervised learning by running many smaller scale experiments on the small image benchmarks SVHN, CIFAR-10 and CIFAR-100, where we achieve results competitive with the state of the art, and where we find evidence that the CowMask perturbation is widely applicable. We open source our code at https://github.com/google-research/google-research/tree/master/milking_cowmask

READ FULL TEXT

page 4

page 5

page 6

research
11/21/2019

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

We improve the recently-proposed "MixMatch" semi-supervised learning alg...
research
07/16/2020

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

Recent state-of-the-art semi-supervised learning (SSL) methods use a com...
research
05/15/2019

ROI Regularization for Semi-supervised and Supervised Learning

We propose ROI regularization (ROIreg) as a semi-supervised learning met...
research
12/10/2021

Revisiting Consistency Regularization for Semi-Supervised Learning

Consistency regularization is one of the most widely-used techniques for...
research
06/14/2018

Improving Consistency-Based Semi-Supervised Learning with Weight Averaging

Recent advances in deep unsupervised learning have renewed interest in s...
research
06/12/2019

Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification

Recent advances in semi-supervised learning methods rely on estimating c...
research
01/18/2021

On Data-Augmentation and Consistency-Based Semi-Supervised Learning

Recently proposed consistency-based Semi-Supervised Learning (SSL) metho...

Please sign up or login with your details

Forgot password? Click here to reset