Explorations in Active Learning Applied to Image Classification

Adriana Klimczak, Marcel Wenka, Maria Ganzha, Marcin Paprzycki

Abstract: While development of very large models is the core of today’s artificial intelligence, very often the cost of model training is being raised. In this context, active learning is pointed to as a method to maximize model quality, while minimizing the amount of resources needed to train it. The aim of this contribution is to systematically compare performance of active learning applied to the image classification task for three datasets.