Error message

Deprecated function: The each() function is deprecated. This message will be suppressed on further calls in menu_set_active_trail() (line 2396 of /var/www/html/htdocs-robdream/includes/menu.inc).

Selecting CNN Features for Online Learning of 3D Objects

Publication Type:

Conference Paper

Source:

IEEE International Conference on Intelligent Robots and Systems, IEEE, Vancouver, BC, Canada (2017)

ISBN:

978-1-5386-2682-5

Accession Number:

17428228

URL:

http://ieeexplore.ieee.org/document/8206393/?reload=true

Keywords:

Computational modeling, Feature extraction, Robots, Support vector machines, Training, Training data, Uncertainty

Abstract:

We present a novel method for classifying 3D objects that is particularly tailored for the requirements in robotic applications. The major challenges here are the comparably small amount of available training data and the fact that often data is perceived in streams and not in fixed-size pools. Traditional state-of-the-art learning methods, however, require a large amount of training data, and their online learning capabilities are usually limited. Therefore, we propose a modality-specific selection of convolutional neural networks (CNN), pre-trained or fine-tuned, in combination with a classifier that is designed particularly for online learning from data streams, namely the Mondrian Forest (MF). We show that this combination of trained features obtained from a CNN can be improved further if a feature selection algorithm is applied. In our experiments, we use the resulting features both with a MF and a linear Support Vector Machine (SVM). With SVM we beat the state of the art on an RGB-D dataset, while with MF a strong result for active learning is achieved.