Adversarial Sampling for Active Learning

Christoph Mayer, Radu Timofte

Abstract: This paper proposes ASAL, a new pool based active learning method that generates high entropy samples. Instead of directly annotating the synthetic samples, ASAL searches similar samples from the pool and includes them for training. Hence, the quality of new samples is high and annotations are reliable. ASAL is particularly suitable for large data sets because it achieves a better run-time complexity (sub-linear) for sample selection than traditional uncertainty sampling (linear). We present a comprehensive set of experiments on two data sets and show that ASAL outperforms similar methods and clearly exceeds the established baseline (random sampling). In the discussion section we analyze in which situations ASAL performs best and why it is sometimes hard to outperform random sample selection. To the best of our knowledge this is the first adversarial active learning technique that is applied for multiple class problems using deep convolutional classifiers and demonstrates superior performance than random sample selection.

Keywords: active learning, adversarial training, GAN

TL;DR: ASAL is a pool based active learning method that generates high entropy samples and retrieves matching samples from the pool in sub-linear time.

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [CelebA](https://paperswithcode.com/dataset/celeba), [LSUN](https://paperswithcode.com/dataset/lsun), [SVHN](https://paperswithcode.com/dataset/svhn)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1808.06671/code)