Perceptual Loss is a loss function commonly used in image style transfer methods based on deep learning. Compared with the traditional mean square error loss function (Mean Square Error, MSE), perceptual loss pays more attention to the perceived quality of the image, which is more in line with the human eye's perception of image quality.
The calculation method of perceptual loss is usually to pass the input image and the target image through the pre-trained neural network to obtain their feature representation in the network. These feature representations are then used as input to a loss function to compute the Euclidean or Manhattan distance between them. The goal of perceptual loss is to minimize the distance between the input image and the target image in feature space.
Among them, x is the input image, y is the target image, Fi(x) and Fi(y) respectively represent their feature representations in the i-th layer of the pre-trained neural network, and N is the number of feature layers.
Perceptual loss can be used in various image processing tasks, such as image super-resolution, image denoising, image inpainting, image style transfer, etc. Article source address https://www.yii666.com/blog/443431.html