LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks
This work addresses efficiency issues in CNNs for image classification, but it is incremental as it builds on existing ResNet frameworks.
The authors tackled the high computational cost of convolutional neural networks by introducing lean convolution operators that reduce parameters and complexity, achieving comparable results to other reduced architectures on three image classification tasks.
Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the training of and prediction with CNNs. To improve the efficiency of CNNs, we introduce lean convolution operators that reduce the number of parameters and computational complexity, and can be used in a wide range of existing CNNs. Here, we exemplify their use in residual networks (ResNets), which have been very reliable for a few years now and analyzed intensively. In our experiments on three image classification problems, the proposed LeanResNet yields results that are comparable to other recently proposed reduced architectures using similar number of parameters.