Driven by GPUs, massive amounts of annotated data and more advanced algorithms, deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems. Among different types of deep neural networks, convolutional neural networks (CNNs) have been most extensively studied. CNNs have recently taken the computer vision community by storm and benefited real-world applications. This monograph presents the CNNs from the aspect of architectures, improvements and applications in 2D computer vision.