Neural network and related methods, media and devices for multi-label recognition of paintings

Abstract

The invention discloses a neural network for multi-label recognition of paintings and related methods, media and equipment. The neural network in the embodiment of the present invention includes: a residual attention network, which is used to receive the painting image and learn the attention area of ​​the image to output a feature map; a content label network, which is used to receive the feature map and output the predicted probability of the content label; The label network is used to receive the feature map and output the predicted probability of the subject label; the category label network is used to receive the feature map and output the predicted probability of the category label. This implementation mode can realize multi-label identification of content, multi-label identification of subject matter and single-label identification of category of painting images.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a neural network for multi-label recognition of paintings, a training method using the neural network, a method for multi-label recognition using the neural network, a storage medium and a computer device. Background technique [0002] Deep learning is one of the most important breakthroughs in artificial intelligence in the last decade. It has achieved great success in speech recognition, natural language processing, computer vision, image and video analysis, multimedia and many other fields. On the ImageNet dataset, the top-5error of ResNet is only 3.75%, which has greatly improved the index compared with traditional recognition methods. Convolutional neural network has powerful learning ability and efficient feature expression ability, and has achieved good results in single-label recognition. However, a real image contains more than one scene and object, so the pro...

AI Technical Summary

Problems solved by technology

[0003] The current existing methods are all based on ordinary photos to generate corresponding content tags or scene tags, without the characteristics of paintings (requires multiple types of tags, including multi-label and single-label; and ordinary photo image recognition does not require multiple similar paintings. class labels) to generate labels, and there is no method of putting single-label and multi-label generation in one network and generating labels at the same time

Images