Unsupervised and Transfer Learning under Uncertainty - From Object Detections to Scene Categorization

Grégoire Mesnil, Salah Rifai, Antoine Bordes, Xavier Glorot, Yoshua Bengio, Pascal Vincent

2013

Abstract

Classifying scenes (e.g. into “street”, “home” or “leisure”) is an important but complicated task nowadays, because images come with variability, ambiguity, and a wide range of illumination or scale conditions. Standard approaches build an intermediate representation of the global image and learn classifiers on it. Recently, it has been proposed to depict an image as an aggregation of its contained objects:the representation on which classifiers are trained is composed of many heterogeneous feature vectors derived from various object detectors. In this paper, we propose to study different approaches to efficiently combine the data extracted by these detectors. We use the features provided by Object-Bank (Li-Jia Li and Fei-Fei, 2010a) (177 different object detectors producing 252 attributes each), and show on several benchmarks for scene categorization that careful combinations, taking into account the structure of the data, allows to greatly improve over original results (from +5% to +11%) while drastically reducing the dimensionality of the representation by 97% (from 44;604 to 1; 000).

Paper Citation

in Harvard Style

Mesnil G., Rifai S., Bordes A., Glorot X., Bengio Y. and Vincent P. (2013). Unsupervised and Transfer Learning under Uncertainty - From Object Detections to Scene Categorization . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 345-354. DOI: 10.5220/0004227803450354

in Bibtex Style

@conference{icpram13,
author={Grégoire Mesnil and Salah Rifai and Antoine Bordes and Xavier Glorot and Yoshua Bengio and Pascal Vincent},
title={Unsupervised and Transfer Learning under Uncertainty - From Object Detections to Scene Categorization},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={345-354},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004227803450354},
isbn={978-989-8565-41-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Unsupervised and Transfer Learning under Uncertainty - From Object Detections to Scene Categorization
SN - 978-989-8565-41-9
AU - Mesnil G.
AU - Rifai S.
AU - Bordes A.
AU - Glorot X.
AU - Bengio Y.
AU - Vincent P.
PY - 2013
SP - 345
EP - 354
DO - 10.5220/0004227803450354