Traditional pattern subgraph retrieval method based on self-attention mechanism

Abstract

The invention discloses a traditional pattern subgraph retrieval method based on a self-attention mechanism. The method comprises the following steps: training a subgraph retrieval model by utilizing a training data set; extracting feature maps of different levels, and fusing the feature maps by using a feature pyramid; extracting global features and local features; attention weight calculation is carried out, and aggregation is carried out on the weighted fusion feature graph to obtain sub-graph features; and calculating the similarity between the query sub-graph features and the database image features, and sorting the database according to the similarity to realize sub-graph retrieval. According to the method, high-level features with rich semantic information and corresponding bottom-level feature maps with rich spatial information are fused, so that a pre-selection box generated by Transform can capture smaller details, an attention mechanism is utilized to calculate self-attention weights for fused features, sub-map feature maps are weighted, most unimportant information is ignored, and the method is more accurate and efficient. Therefore, a better retrieval result can be obtained.

Description

technical field [0001] The invention relates to the technical fields of image processing and computer vision, in particular to a traditional pattern subimage retrieval method based on a self-attention mechanism. Background technique [0002] With the development of the network and digital economy, multimedia data is also growing rapidly. More and more data can be saved in the form of images, and the types are more complex. How to find the images you need in a large number of images has become a difficult problem. Image retrieval has been a very active research area since the 1970s. Image retrieval methods can be divided into two categories: text-based image retrieval (TBIR) and content-based image retrieval (CBIR). The full visual content in an image is sometimes difficult to express in words, so TBIR can produce irrelevant results. CBIR refers to the retrieval of images using information such as color, texture, contour, and spatial relationship of the image. [0003] With...

AI Technical Summary

Problems solved by technology

However, this method has problems such as high feature dimension and limited image input.

Images