Compression is a standard procedure for making convolutional neural networks (CNNs) adhere to some specific computing resource constraints. However, searching for a compressed architecture typically involves a series of time-consuming training/validation experiments to determine a good compromise between network size and performance accuracy. To address this, we propose an image complexity-guided network compression technique for biomedical image segmentation. Given any resource constraints, our framework utilizes data complexity and network architecture to quickly estimate a compressed model which does not require network training. Specifically, we map the dataset complexity to the target network accuracy degradation caused by compression. Such mapping enables us to predict the final accuracy for different network sizes, based on the computed dataset complexity. Thus, one may choose a solution that meets both the network size and segmentation accuracy requirements. Finally, the mapping is used to determine the convolutional layer-wise multiplicative factor for generating a compressed network. We conduct experiments using 5 datasets, employing 3 commonly-used CNN architectures for biomedical image segmentation as representative networks. Our proposed framework is shown to be effective for generating compressed segmentation networks, retaining up to $\approx 95\%$ of the full-sized network segmentation accuracy, and at the same time, utilizing $\approx 32x$ fewer network trainable weights (average reduction) of the full-sized networks.
翻译:压缩是一个使神经神经网络(CNNs)遵守某些特定计算资源限制的标准程序。然而,寻找压缩结构通常需要一系列耗时的培训/验证实验,以确定网络规模和性能准确性之间的良好折中。为此,我们建议采用图像复杂引导网络压缩压缩技术进行生物医学图像分割。鉴于任何资源限制,我们的框架利用数据复杂性和网络架构快速估计压缩模型,不需要网络培训。具体地说,我们将数据集的复杂程度与压缩造成的目标网络精确性降解相匹配。这种绘图使我们能够根据计算数据集的复杂性,预测不同网络规模的最终准确性。因此,人们可以选择一种既符合网络规模要求又符合分层准确性要求的解决办法。最后,我们用这一绘图来确定产生压缩网络的递增层多倍增系数。我们使用5个数据集进行实验,使用3个常用的CNN结构进行生物医学图像分割,作为具有代表性的网络。我们提议的框架显示,可以有效地生成压缩的分解网络网络,将保持到$/Approx的准确度,将网络的完整比例降低至美元,将网络的精度降低到35x的精度。