The invention relates to a network training method and device and an image processing method and device. The network training method comprises the steps that a sample image in a training set and a transformed image of the sample image are input into a first network to be processed, a first processing result of the sample image and a second processing result of the transformed image are obtained, and the transformed image is obtained by conducting geometric transformation on the sample image; the transformed image of the sample image is inputted into a pre-trained second network for processingto obtain a third processing result of the transformed image; and the first network is trained according to the annotation results and the first processing result of the plurality of sample images andthe second processing result and the third processing result of the transformed images of the plurality of sample images. According to the embodiment of the invention, the performance of the trainedstudent network can be improved.
更多
查看译文
关键词
Image processing,Geometric transformation,Computer vision,Annotation,Computer science,Artificial intelligence,Sample image,Training methods,Training set