| Abstrakt: |
In this contribution, we explore the possibilities of learning in large-scale, multimodal processing systems operating under real-world conditions. Using an instance of a large-scale object detection system for complex traffic scenes, we demonstrate that there is a great deal of very robust correlations between high-level processing results quantities, and that such correlations can be autonomously detected and exploited to improve performance. We formulate requirements for performing system-level learning (online operation, scalability to high-dimensional inputs, data mining ability, generality and simplicity) and present a suitable neural learning strategy. We apply this method to infer the identity of objects from multimodal object properties (˵context″) computed within the correlated system and demonstrate strong performance improvements as well as significant generalization. Finally, we compare our approach to state-of-the-art learning methods, Locally Weighted Projection Regression (LWPR) and Multilayer Perceptron (MLP), and discuss the results in terms of the requirements for system-level learning. [ABSTRACT FROM AUTHOR] |
