This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Active MAP Inference in CRFs for Efficient Semantic Segmentation

Gemma Roig, Xavier Boix, Roderick de Nijs, Sebastian Ramos, Kolja Kühnlenz and Luc Van Gool
ICCV (oral)


Most MAP inference algorithms for CRFs optimize an energy function knowing all the potentials. In this paper, we focus on CRFs where the computational cost of instantiating the potentials is orders of magnitude higher than MAP inference. This is often the case in semantic image segmentation, where most potentials are instantiated by slow classifiers fed with costly features. We introduce Active MAP inference 1) to on-the-fly select a subset of potentials to be instantiated in the energy function, leaving the rest of the parameters of the potentials unknown, and 2) to estimate the MAP labeling from such incomplete energy function. Results for semantic segmentation benchmarks, namely PASCAL VOC 2010 and MSRC-21~\cite{Shotton09}, show that Active MAP inference achieves similar levels of accuracy but with major efficiency gains.

Link to publisher's page
  author = {Gemma Roig and Xavier Boix and Roderick de Nijs and Sebastian Ramos and Kolja K\"uhnlenz and Luc Van Gool},
  title = {Active MAP Inference in CRFs for Efficient Semantic Segmentation},
  booktitle = {ICCV (oral)},
  year = {2013},
  keywords = {}