Scalable Multitask Representation Learning for Scene Classification

Maksim Lapin, Bernt Schiele, Matthias Hein; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 1434-1441

Abstract


The underlying idea of multitask learning is that learning tasks jointly is better than learning each task individually. In particular, if only a few training examples are available for each task, sharing a jointly trained representation improves classification performance. In this paper, we propose a novel multitask learning method that learns a low-dimensional representation jointly with the corresponding classifiers, which are then able to profit from the latent inter-class correlations. Our method scales with respect to the original feature dimension and can be used with high-dimensional image descriptors such as the Fisher Vector. Furthermore, it consistently outperforms the current state of the art on the SUN397 scene classification benchmark with varying amounts of training data.

Related Material


[pdf]
[bibtex]
@InProceedings{Lapin_2014_CVPR,
author = {Lapin, Maksim and Schiele, Bernt and Hein, Matthias},
title = {Scalable Multitask Representation Learning for Scene Classification},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}
}