Depth neural network (DNN) has become a research hotspot in the field of image recognition. Developing a suitable solution to\nintroduce effective operations and layers into DNN model is of great significance to improve the performance of image and video\nrecognition. To achieve this, through making full use of block information of different sizes and scales in the image, a multiscale\npooling deep convolution neural network model is designed in this paper. No matter how large the feature map is, multiscale\nsampling layer will output three fixed-size character matrices. Experimental results demonstrate that this method greatly improves\nthe performance of the current single training image, which is suitable for solving the image generation, style migration, image\nediting, and other issues. It provides an effective solution for further industrial practice in the fields of medical image, remote\nsensing, and satellite imaging.
Loading....