Combining MixMatch and Active Learning for Better Accuracy with Fewer Labels

12/02/2019
by   Shuang Song, et al.
0

We propose using active learning based techniques to further improve the state-of-the-art semi-supervised learning MixMatch algorithm. We provide a thorough empirical evaluation of several active-learning and baseline methods, which successfully demonstrate a significant improvement on the benchmark CIFAR-10, CIFAR-100, and SVHN datasets (as much as 1.5 We also provide an empirical analysis of the cost trade-off between incrementally gathering more labeled versus unlabeled data. This analysis can be used to measure the relative value of labeled/unlabeled data at different points of the learning curve, where we find that although the incremental value of labeled data can be as much as 20x that of unlabeled, it quickly diminishes to less than 3x once more than 2,000 labeled example are observed. Code can be found at https://github.com/google-research/mma.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/26/2019

The Use of Unlabeled Data versus Labeled Data for Stopping Active Learning for Text Classification

Annotation of training data is the major bottleneck in the creation of t...
research
11/19/2019

Rethinking deep active learning: Using unlabeled data at model training

Active learning typically focuses on training a model on few labeled exa...
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
11/30/2022

An Empirical Study on the Efficacy of Deep Active Learning for Image Classification

Deep Active Learning (DAL) has been advocated as a promising method to r...
research
06/15/2023

Re-Benchmarking Pool-Based Active Learning for Binary Classification

Active learning is a paradigm that significantly enhances the performanc...
research
06/16/2023

LabelBench: A Comprehensive Framework for Benchmarking Label-Efficient Learning

Labeled data are critical to modern machine learning applications, but o...
research
12/02/2020

Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning

Active learning is widely used to reduce labeling effort and training ti...

Please sign up or login with your details

Forgot password? Click here to reset