Deep Bayesian Active Semi-Supervised Learning

03/03/2018
by   Matthias Rottmann, et al.
0

In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to achieve high generalization performance from a deep convolutional neural network with as few known labels as possible. In a setting where a small amount of labeled data as well as a large amount of unlabeled data is available, our method first learns the labeled data set. This initialization is followed by an expectation maximization algorithm, where further training reduces classification entropy on the unlabeled data by targeting a low entropy fit which is consistent with the labeled data. In addition the algorithm asks at a specified frequency an oracle for labels of data with entropy above a certain entropy quantile. Using this active learning component we obtain an agile labeling process that achieves high accuracy, but requires only a small amount of known labels. For the MNIST dataset we report an error rate of 2.06 results are obtained without employing any special network architecture or data augmentation.

READ FULL TEXT
research
02/05/2020

Rényi Entropy Bounds on the Active Learning Cost-Performance Tradeoff

Semi-supervised classification, one of the most prominent fields in mach...
research
08/26/2021

Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networks

This paper is concerned with image classification based on deep convolut...
research
05/06/2019

MixMatch: A Holistic Approach to Semi-Supervised Learning

Semi-supervised learning has proven to be a powerful paradigm for levera...
research
02/12/2018

Fast Interactive Image Retrieval using large-scale unlabeled data

An interactive image retrieval system learns which images in the databas...
research
06/17/2019

Active Learning by Greedy Split and Label Exploration

Annotating large unlabeled datasets can be a major bottleneck for machin...
research
05/26/2018

Transductive Label Augmentation for Improved Deep Network Learning

A major impediment to the application of deep learning to real-world pro...
research
04/28/2022

On tuning a mean-field model for semi-supervised classification

Semi-supervised learning (SSL) has become an interesting research area d...

Please sign up or login with your details

Forgot password? Click here to reset