A ship target classification method based on deep feature collaboration
A deep feature collaborative ship target classification algorithm is proposed to address the issues of poor per-formance in fine-grained ship classification and poor learning of ship image features in existing ship target classification methods.Firstly,build a dual branch ResNet-18 network structure;Then,the idea of contrastive learning is introduced to achieve complementary feature information between two branches,enriching the learning of ship image features;Finally,through the feature collaboration module,the learned dual branch contrastive features are deeply integrated to minimize clas-sification loss and improve classification results.A large number of experimental results on the ship image dataset FGSC-23 show that the average accuracy of classifying 23 types of fine-grained ship images reaches 83.56％.
deep feature collaborationcomparative learningship target classification
NETL
NSTL
万方数据
