Zero-sample image classification and recognition method based on multi-part attention mechanism

Abstract

The invention discloses a zero-sample image classification and recognition method based on a multi-part attention mechanism, and the method comprises the following steps: S1, training a multi-part convolution detector; s2, training a semantic feature extractor; s3, acquiring pictures of the training set, and processing the pictures by training an attention detector; s4, carrying out loss calculation; and S5, repeating the calculation of the steps S3 and S4, performing testing when the algorithm loss is lower than a preset value, and selecting the minimum distance as a category value. Accordingto the method, a semantic segmentation mode is adopted, firstly, semantic segmentation is carried out on the whole picture to obtain effective parts, unnecessary redundant information is screened out, and then feature extraction is carried out on the multiple parts; for different parts, an attention mechanism is put forward to act on the different parts for weighting, so that each sample has a different weighting mode, and therefore, for each sample, parts with high weights can be generated, and the parts can better distinguish the parts from other types.

Description

technical field [0001] The present invention relates to the field of electric power, and more specifically, relates to a zero-sample image classification and recognition method based on a multi-part attention mechanism. Background technique [0002] With the rise of big data and large-scale data learning in recent years, traditional image recognition techniques are gradually unable to meet new image recognition requirements. For example, categories that have not appeared in the training set appear during the test process. It is particularly prominent in the data, because the large-scale data volume is a large-scale category, and there are multiple subcategories under a category. Therefore, it is of great practical significance to improve the image classification problem under zero sample. In order to improve the recognition rate of training unseen categories, a bilinear model is proposed to establish the connection from visible to unseen categories through auxiliary informa...

AI Technical Summary

Problems solved by technology

The previous classification process did not pay attention to this problem, which affected the subsequent classification process

Images