Watermark detection method, apparatus, computer device, and storage medium

The present application relates to a watermark detection method, apparatus, computer device and storage medium. The method comprises the following steps of: inputting the image to be detected into a trained coarse-grained segmentation network model for detection, and obtaining a characteristic map of the image to be detected output by each network channel in the coarse-grained segmentation networkmodel, wherein each network channel corresponds to a watermark class; according to the characteristic map and the network channel, the watermark category in the image to be detected and the positionof the watermark in the image to be detected are determined. The method can detect multiple watermarks simultaneously and detect the specific position of the watermark in the image. 本申请涉及种水印检测方法、装置、计算机设备和存储介质。方法包括：将待检测图像输入训练好的粗粒度分割网络模型中进行检测，得到粗粒度分割网络模型中的各网络通道输出的待检测图像的特征图；其中，每网络通道与水印类别对应；根据特征图及网络通道确定待检测图像中的水印的类别及水印在待检测图像中的位置。采用本方法能够同时检测出多个类别的水印，并检测出水印在图像中的具体位置。