Clustering Learning for Robotic Vision
This work addresses efficiency in robotic vision systems, though it appears incremental as it applies an existing unsupervised method to a specific domain.
The paper tackles the problem of training deep neural networks for robotic vision by applying clustering learning, an unsupervised technique that reduces training time to minutes and uses fewer parameters while outperforming larger networks trained for hours on complex datasets.
We present the clustering learning technique applied to multi-layer feedforward deep neural networks. We show that this unsupervised learning technique can compute network filters with only a few minutes and a much reduced set of parameters. The goal of this paper is to promote the technique for general-purpose robotic vision systems. We report its use in static image datasets and object tracking datasets. We show that networks trained with clustering learning can outperform large networks trained for many hours on complex datasets.