Cluster-Based Active Learning

12/31/2018
by   Fábio Perez, et al.
0

In this work, we introduce Cluster-Based Active Learning, a novel framework that employs clustering to boost active learning by reducing the number of human interactions required to train deep neural networks. Instead of annotating single samples individually, humans can also label clusters, producing a higher number of annotated samples with the cost of a small label error. Our experiments show that the proposed framework requires 82 less human interactions for CIFAR-10 and EuroSAT datasets respectively when compared with the fully-supervised training while maintaining similar performance on the test set.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset