Deep Convolutional Neural Network Ensembles Using ECOC
Deep Convolutional Neural Network Ensembles Using ECOC
复制标题
DOI：
10.1109/access.2021.3088717
复制
发表时间：
2020-09
期刊：
影响因子：
3.9
通讯作者：
Sara Atito Ali Ahmed;Cemre Zor;Muhammad Awais;B. Yanikoglu;J. Kittler
中科院分区：
文献类型：
--
作者：
Sara Atito Ali Ahmed;Cemre Zor;Muhammad Awais;B. Yanikoglu;J. Kittler
深度神经网络在许多应用中提高了决策系统的性能，包括图像理解，并且可以通过构造集成来获得进一步的收益。然而，由于训练网络所需的时间通常非常高，或者获得的性能收益不是非常显著，因此设计深度网络的集成通常不是很有好处。本文分析了一种用于构建深度网络集成的纠错输出编码(ECOC)框架，并提出了不同的设计策略来解决精度和复杂性之间的权衡。我们对引入的ECOC设计和最先进的集成技术，如集成平均和梯度提升决策树进行了广泛的比较研究。此外，我们还提出了一种融合技术，可以获得最高的分类性能。
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 generally very high or the performance gain obtained is not very significant. In this paper, we analyse an error correcting output coding (ECOC) framework for constructing ensembles of 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 fusion technique, that is shown to achieve the highest classification performance.