Deep Convolutional Neural Network Ensembles using ECOC
This work addresses the problem of improving ensemble performance for deep networks in applications like image understanding, though it appears incremental as it builds on existing ECOC methods.
The paper tackles the challenge of designing effective ensembles for deep neural networks by analyzing and proposing strategies within the error correcting output coding (ECOC) framework to balance accuracy and complexity, with a combinatory technique achieving the highest classification performance in comparative studies.
Deep neural networks have enhanced the performance of decision making systems in many applications including image understanding, and further gains can be achieved by constructing ensembles. However, designing an ensemble of deep networks is often not very beneficial since the time needed to train the networks is very high or the performance gain obtained is not very significant. In this paper, we analyse error correcting output coding (ECOC) framework to be used as an ensemble technique for deep networks and propose different design strategies to address the accuracy-complexity trade-off. We carry out an extensive comparative study between the introduced ECOC designs and the state-of-the-art ensemble techniques such as ensemble averaging and gradient boosting decision trees. Furthermore, we propose a combinatory technique which is shown to achieve the highest classification performance amongst all.