Adversarial Representation Active Learning
This work addresses the challenge of reducing labeling costs for training deep neural networks, offering a more efficient method for applications requiring large-scale data annotation.
The paper tackles the problem of label-efficient training in active learning by using deep generative models to incorporate labeled, unlabeled, and generated images for co-training, resulting in significantly higher classification accuracy with fewer labels across multiple datasets.
Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that allows more effective use of computational and human resources for labeling and training deep neural networks. In this work, we demonstrate how we can use recent advances in deep generative models, to outperform the state-of-the-art in achieving the highest classification accuracy using as few labels as possible. Unlike previous approaches, our approach uses not only labeled images to train the classifier but also unlabeled images and generated images for co-training the whole model. Our experiments show that the proposed method significantly outperforms existing approaches in active learning on a wide range of datasets (MNIST, CIFAR-10, SVHN, CelebA, and ImageNet).