A small sample target recognition method based on hybrid attribute learning

Abstract

The invention discloses a small sample target recognition method based on hybrid attribute learning. The method comprises at first, semantic attributes are defined and auxiliary samples are obtained;the target training samples are inputted into the feature sub-network for obtaining hidden attributes, and the hidden attributes of the target training samples are outputted; the auxiliary sample is input to a feature subnetwork for obtaining semantic attributes, which is used to obtain the semantic attributes of the auxiliary sample; the extracted features are dictionary-learned to obtain the encoding of the features, wherein the encoded data including semantic attributes and hidden attributes are input into a multi-classifier for classification training to obtain a classification network, which is used for subsequent classification of the target. This method overcomes the shortcomings of the other methods which only have good interpretability and poor discriminating ability, or only havegood discriminating ability and poor interpreting ability, and synthesizes the advantages of semantic attributes and hidden attributes, and gives attention to both interpretability and discriminatingability.

Description

technical field [0001] The invention belongs to the field of target recognition, and relates to a small-sample target recognition method based on mixed attribute (semantic attribute / hidden attribute) learning. Background technique [0002] Small-sample target recognition: The target recognition model related to deep learning is data-driven, and the small sample size hinders the accuracy of model recognition. Small-sample target recognition has become a research hotspot. Existing small-sample object recognition methods do not comprehensively consider interpretability and discriminative ability. Models with good interpretability usually have poor discriminative ability; models with good discriminative ability usually have poor interpretability. [0003] Attribute learning: Attribute learning is a learning method by establishing the relationship between underlying features and attributes, and the relationship between attributes and categories. Attribute learning can integrate...

AI Technical Summary

Problems solved by technology

This method overcomes the shortcomings of other methods that only have good interpretability but poor discrimination ability, or only have good discrimination ability but poor interpretability. It combines the advantages of semantic attributes and latent Discrimination ability

Images