The advent of convolutional neural networks (CNNs) has accelerated the progress of computer vision from many aspects. However, the majority of the existing CNNs heavily rely on expensive GPUs (graphics processing units). to support large computations. Therefore, CNNs have not been widely used to inspect surface defects in the manufacturing field yet. In this paper, we develop a compact CNN-based model that not only achieves high performance on tiny defect inspection but can be run on low-frequency CPUs (central processing units). Our model consists of a light-weight (LW) bottleneck and a decoder. By a pyramid of lightweight kernels, the LW bottleneck provides rich features with less computational cost. The decoder is also built in a lightweight way, which consists of an atrous spatial pyramid pooling (ASPP) and depthwise separable convolution layers. These lightweight designs reduce the redundant weights and computation greatly. We train our models on groups of surface datasets. The model can successfully classify/segment surface defects with an Intel i3-4010U CPU within 30 ms. Our model obtains similar accuracy with MobileNetV2 while only has less than its 1/3 FLOPs (floating-point operations per second) and 1/8 weights. Our experiments indicate CNNs can be compact and hardware-friendly for future applications in the automated surface inspection (ASI).

中文翻译：

---

用于表面缺陷检查的紧凑型卷积神经网络。

卷积神经网络（CNN）的出现从许多方面加速了计算机视觉的发展。但是，大多数现有的CNN严重依赖昂贵的GPU（图形处理单元）。支持大型计算。因此，CNN尚未在制造领域中广泛用于检查表面缺陷。在本文中，我们开发了一个基于CNN的紧凑模型，该模型不仅可以在微小缺陷检查中实现高性能，而且可以在低频CPU（中央处理器）上运行。我们的模型包括一个轻量级（LW）瓶颈和一个解码器。通过轻量级内核金字塔，LW瓶颈以更少的计算成本提供了丰富的功能。解码器也以轻巧的方式构建，它由一个无孔的空间金字塔池（ASPP）和深度可分离的卷积层组成。这些轻巧的设计大大减少了冗余权重和计算量。我们在表面数据集组上训练模型。该模型可以在30毫秒内使用Intel i3-4010U CPU成功地分类/细分表面缺陷。我们的模型在MobileNetV2上获得了相似的精度，但只有不到其1/3 FLOP（每秒浮点运算）和1/8权重。我们的实验表明，CNN可以紧凑且对硬件友好，可用于将来在自动表面检测（ASI）中的应用。我们的模型在MobileNetV2上获得了相似的精度，但只有不到其1/3 FLOP（每秒浮点运算）和1/8权重。我们的实验表明，CNN可以紧凑且对硬件友好，可用于将来在自动表面检测（ASI）中的应用。我们的模型在MobileNetV2上获得了相似的精度，但只有不到其1/3 FLOP（每秒浮点运算）和1/8权重。我们的实验表明，CNN可以紧凑且对硬件友好，适合将来在自动表面检测（ASI）中的应用。