A simple technique for improving multi-class classification with neural networks
This addresses multi-class classification challenges in neural networks, particularly for gesture recognition, though it appears incremental as it builds on standard one-against-all methods.
The paper tackles multi-class classification by adding a second network layer that classifies initial class scores to disambiguate hard-to-separate classes, achieving significant performance improvements on a challenging 10-class 3D hand gesture recognition task.
We present a novel method to perform multi-class pattern classification with neural networks and test it on a challenging 3D hand gesture recognition problem. Our method consists of a standard one-against-all (OAA) classification, followed by another network layer classifying the resulting class scores, possibly augmented by the original raw input vector. This allows the network to disambiguate hard-to-separate classes as the distribution of class scores carries considerable information as well, and is in fact often used for assessing the confidence of a decision. We show that by this approach we are able to significantly boost our results, overall as well as for particular difficult cases, on the hard 10-class gesture classification task.