Adversarial Representation Active Learning
arXiv:1912.09720
Abstract
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).
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Adversarial Feature Learning
- Cost-Effective Active Learning for Deep Image Classification
- Adversarially Learned Inference
- Bayesian Active Learning for Classification and Preference Learning
- Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
- Generative Adversarial Active Learning
- Bayesian Batch Active Learning as Sparse Subset Approximation
- Gradient-free Policy Architecture Search and Adaptation