Ensembles of feedforward-designed convolutional neural networks
This work addresses image classification accuracy, particularly for hard samples, but is incremental as it builds on existing ensemble and CNN techniques.
The authors tackled image classification by proposing an ensemble method that fuses outputs from multiple feedforward-designed convolutional neural networks, using strategies like diverse parameter settings and partitioning samples by confidence to boost accuracy, achieving improved results on MNIST and CIFAR-10 datasets.
An ensemble method that fuses the output decision vectors of multiple feedforward-designed convolutional neural networks (FF-CNNs) to solve the image classification problem is proposed in this work. To enhance the performance of the ensemble system, it is critical to increasing the diversity of FF-CNN models. To achieve this objective, we introduce diversities by adopting three strategies: 1) different parameter settings in convolutional layers, 2) flexible feature subsets fed into the Fully-connected (FC) layers, and 3) multiple image embeddings of the same input source. Furthermore, we partition input samples into easy and hard ones based on their decision confidence scores. As a result, we can develop a new ensemble system tailored to hard samples to further boost classification accuracy. Experiments are conducted on the MNIST and CIFAR-10 datasets to demonstrate the effectiveness of the ensemble method.