A CNN-based Feature Space for Semi-supervised Incremental Learning in Assisted Living Applications

• Main Authors: Scheck, Tobias, Grassi, Ana Perez, Hirtz, Gangolf
• Format: Journal Article
• Language: English
• Published: 11-11-2020
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2011.05734

A Convolutional Neural Network (CNN) is sometimes confronted with objects of
changing appearance ( new instances) that exceed its generalization capability.
This requires the CNN to incorporate new knowledge, i.e., to learn
incrementally. In this paper, we are concerned with this problem in the context
of assisted living. We propose using the feature space that results from the
training dataset to automatically label problematic images that could not be
properly recognized by the CNN. The idea is to exploit the extra information in
the feature space for a semi-supervised labeling and to employ problematic
images to improve the CNN's classification model. Among other benefits, the
resulting semi-supervised incremental learning process allows improving the
classification accuracy of new instances by 40% as illustrated by extensive
experiments.