High demand for computational power significantly limits the possibility of using modern deep learning methods in the environments where one has to deal with devices limited by the performance and the energy constraints. To address this issue, this paper proposes a novel method of combining the pruning and the transfer learning (TL) techniques for the purpose of delivering solid accuracy while simultaneously lowering the demand for energy and computing power. This method is referred to as finicky TL as it is finicky during the process of selecting filters from a pretrained feature extractor to compose a sparser architecture. The proposed filter selection process is based on an original approach utilizing the Jaccard similarity coefficient calculated between the activation maps and the masks obtained by semantic segmentation. This enables the use of convolutional neural networks, trained previously on a large generic dataset, in a crack classification task. The presented method significantly lowers the inference time while maintaining or even slightly increasing the classification accuracy, enabling real-time operation on single-board computers.

中文翻译：

---

挑剔的迁移学习——一种修剪卷积神经网络的方法，用于边缘设备上的裂缝分类

对计算能力的高需求极大地限制了在必须处理受性能和能量限制的设备的环境中使用现代深度学习方法的可能性。为了解决这个问题，本文提出了一种结合剪枝和迁移学习（TL）技术的新方法，以提供可靠的准确性，同时降低对能量和计算能力的需求。这种方法被称为挑剔 TL，因为它在从预训练的特征提取器中选择过滤器以构成更稀疏的架构的过程中是挑剔的。所提出的过滤器选择过程基于利用激活图和语义分割获得的掩码之间计算的 Jaccard 相似系数的原始方法。这使得之前在大型通用数据集上训练的卷积神经网络能够用于裂缝分类任务。所提出的方法显着降低了推理时间，同时保持甚至略微提高了分类精度，实现了在单板计算机上的实时操作。