SI-GAT: A method based on improved Graph Attention Network for sonar image classification
This is an incremental improvement for sonar image classification, addressing limitations of existing deep learning methods that only consider local features in Euclidean space.
The paper tackles sonar image classification by proposing SI-GAT, an improved Graph Attention Network that operates in non-Euclidean space to capture correlations between nodes based on color and spatial proximity, and it outperforms several CNN methods on real data.
The existing sonar image classification methods based on deep learning are often analyzed in Euclidean space, only considering the local image features. For this reason, this paper presents a sonar classification method based on improved Graph Attention Network (GAT), namely SI-GAT, which is applicable to multiple types imaging sonar. This method quantifies the correlation relationship between nodes based on the joint calculation of color proximity and spatial proximity that represent the sonar characteristics in non-Euclidean space, then the KNN (K-Nearest Neighbor) algorithm is used to determine the neighborhood range and adjacency matrix in the graph attention mechanism, which are jointly considered with the attention coefficient matrix to construct the key part of the SI-GAT. This SI-GAT is superior to several CNN (Convolutional Neural Network) methods based on Euclidean space through validation of real data.