RALF: A reinforced active learning formulation for object class recognition

  • Ebert S
  • Fritz M
  • Schiele B
  • 88


    Mendeley users who have this article in their library.
  • 25


    Citations of this article.


Active learning aims to reduce the amount of labels re- quired for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the labeling process that depends – among other things – on the classification task, the distribution of the data and the employed classification scheme. In this paper, we analyze different sampling criteria including a novel density-based criteria and demonstrate the importance to combine explo- ration and exploitation sampling criteria. We also show that a time-varying combination of sampling criteria often improves performance. Finally, by formulating the criteria selection as a Markov decision process, we propose a novel feedback-driven framework based on reinforcement learn- ing. Our method does not require prior information on the dataset or the sampling criteria but rather is able to adapt the sampling strategy during the learning process by expe- rience. We evaluate our approach on three challenging ob- ject recognition datasets and show superior performance to previous active learning methods.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


  • Sandra Ebert

  • Mario Fritz

  • Bernt Schiele

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free