Small Sample Image Classification Based on Sparse-Attention Relation Network
To solve the problem of small sample image classification,a Sparse Attention Relationship Network(SARN)model was proposed based on the local connectivity of convolution operations and the attention mechanism on the basic of non-local operations.In the process of non-local operation,the sparse strategy is used to calculate the relevant features involved in the response calculation.The dependence between the relevant features of different spatial locations is established through the sparse attention mechanism,and the connection of semantical irrelevant features is cut off.The subsequent convolution operation suppresses the interference of irrelevant information when performing feature measurement on semantical relevant features of different spacial positions,and improves the overall measurement ability of the model.Through a series of experiments on the Mini-ImageNet and Tiered-Ima-geNet datasets,it is found that SARN achieves significant performance improvement compared with small sample learning model.
small sample learningmetric learningrelation networksparse attention mechanismdual attention mechanism
国家科技期刊平台
NSTL
万方数据
维普
