Corpus ID: 59291931

Weakly Supervised Active Learning with Cluster Annotation.

  title={Weakly Supervised Active Learning with Cluster Annotation.},
  author={F{\'a}bio Perez and R. Lebret and K. Aberer},
  journal={arXiv: Learning},
In this work, we introduce a novel framework that employs cluster annotation 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% and 87% less human interactions for CIFAR-10 and EuroSAT datasets respectively… Expand


Cost-Effective Active Learning for Deep Image Classification
Exploring the Limits of Weakly Supervised Pretraining
Active Learning with Clustering and Unsupervised Feature Learning
Active Learning for Convolutional Neural Networks: A Core-Set Approach
The Power of Ensembles for Active Learning in Image Classification
Learning Multiple Layers of Features from Tiny Images
Deep Bayesian Active Learning with Image Data
Deep Residual Learning for Image Recognition
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning