Oil plays an important role in the gearbox, traction transformer, hydraulic damper, and other key components of high-speed trains. Once oil leakage occurs, it indicates that some faults may happen and even affect the normal operation of high-speed trains, thus posing a threat to the safety of the train. Therefore, we can detect the oil stains to discover leaks or find some faults in these components to eliminate potential threats in time. Oil stains have the properties of irregular shapes and huge differences in size, and the internal environment of the train is complex and composed of various parts so it is difficult to detect oil stains. This article proposes a novel methodology to detect oil stains, named progressive context comprehension network (PCCN). The upsampling augmentation module (UAM) and feature refinement module (FRM) are proposed to augment features by strengthening the long short-term contextual relationship of features from multilevels. The pyramid context fusion module (PCFM) is proposed to fuse features by progressively integrating adjacent features, which makes features of each level richer. Moreover, a loss function is applied to instruct the network to learn the characteristics of oil stains in the case of extremely uneven distribution of oil stains and background. Experiment results show that our network achieves better performance such as mean intersection over union (mIoU) and F1-Score with a minimal number of parameters and floating-point operations per seconds (FLOPs) than advanced semantic segmentation methods. Besides, we apply our proposed network to five public saliency datasets and achieve better performance, which demonstrates the adaptability and effectiveness of our method as well.