Details

Autor(en) / Beteiligte

• Mayer, Christoph
• Timofte, Radu

Titel

Adversarial Sampling for Active Learning

Ist Teil von

• 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, p.3060-3068

Ort / Verlag

IEEE

Erscheinungsjahr

2020

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• This paper proposes ASAL, a new GAN 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. To the best of our knowledge, ASAL is the first GAN based AL method applicable to multi-class problems that outperforms random sample selection. Another benefit of ASAL is its small run-time complexity (sub-linear) compared to traditional uncertainty sampling (linear). We present a comprehensive set of experiments on multiple traditional 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.