You are here

Semantic Labelling with Deep Learning - Decision Forests

Related Activities

We investigate how to deploy representation learning within the framework of decision forests, which are ensembles of binary decision trees that have become very popular in computer vision.

Publications:

M. Vestner,  E. Rodola', T.. WindHeuser, S. Rota~Bulo', D. Cremers: Applying Random Forests to the Problem of Dense Non-rigid Shape Correspondence, in Perspectives in Shape Analysis, Springer 2016

M. Chowdury,  S. RotaBulo, R. Moreno, M.K. Kundu, O. Smedby: An Efficient Radiographic Image Retrieval System Using Convolutional Neural Network, International Conference on Pattern Recognition - ICPR, Cancun, Mexico, December 2016

P. Kontschieder, M. Fiterau, A. Criminisi, S. Rota Bulò: Deep Neural Decision Forests. International Conference on Computer Vision - ICCV, Santiago, Chile, December 13-16, 2015 - David Marr prize for outstanding computer vision research

S. Rota Bulo', P. Kontschieder: Neural Decision Forests for Semantic Image Labelling. Computer Vision and Pattern Recognition - CVPR, Columbus, Ohio, USA, 24-27 June 2014

P. Kontschieder, S. Rota Bulo', M. Pelillo, H. Bischof: Structured Labels in Random Forests for Semantic Labelling and Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014