Method and device for establishing multi-attribute recognition model and method for multi-attribute recognition

Abstract

The embodiment of the invention provides a method for establishing a multi-attribute recognition model, a device and a multi-attribute recognition method. The method comprises the following steps: inputting a sample image labeled with multi-attributes in advance to a first model for learning, and obtaining a characteristic matrix of each image in the sample image; the feature matrix of each imagebeing input to the second model for learning to obtain the semantics of each image; the first predictive value of each attribute being obtained according to the feature matrix, and the second predictive value of each attribute being obtained according to the semantic- spatial eigenmatrix; obtaining a second prediction value of each attribute by a spatial feature matrix, weighting and summing the first prediction value and the second prediction value to obtain a comprehensive prediction value of each attribute of each image; when the loss between the synthesized prediction value and the label value is stable in the preset threshold range, the multi-attribute recognition model can be obtained by learning. The embodiment of the invention can effectively utilize the labeling information to obtain the spatial and semantic association of the multiple attributes, and the recognition accuracy is high.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of machine learning, and more specifically, relate to a method and device for establishing a multi-attribute recognition model and a multi-attribute recognition method. Background technique [0002] Traditional pedestrian multi-attribute recognition methods include multi-label SVM and Softmax classifier methods, but the accuracy of these methods is not as high as convolutional neural networks. [0003] At present, the methods of using convolutional neural network for multi-attribute recognition mainly include: 1) Using the form of single-attribute multi-model, one model identifies one attribute in a targeted manner, and finally integrates the output results of multiple models to complete multi-attribute recognition ; 2) Adopt the form of multi-label, such as using deep learning frameworks such as MxNet and Pytorch, and directly input multiple labels for learning. During the training pro...

AI Technical Summary

Problems solved by technology

[0004] Using a single-attribute multi-model method to achieve multi-attribute recognition is not efficient; based on the existing deep learning framework, multi-label learning is used to treat all attributes of the entire image equally, ignoring the correlation between attributes. The complex and diverse content in multi-label images makes it difficult to learn effective feature representations and classifiers; dividing images into regions also ignores the correlation between attributes, and the implementation of region proposals is relatively complicated and not very practical

Images