Fine-grained image recognition method based on multi-target Lagrange regularization

Abstract

The invention discloses a fine-grained image recognition method based on multi-target Lagrange regularization, and the method comprises the steps: extracting an image feature X of an input image through a neural network, and obtaining a corresponding bilinear image A; obtaining a regularization feature Y from the bilinear image A, and constructing a target function containing a matrix square root,a low rank and a sparse constraint item; introducing two auxiliary variables to weaken the relevance among the three constraint items, converting the target function into an augmented Lagrange form,and alternately optimizing each matrix constraint item to obtain a global approximate optimal solution; and utilizing the global approximate optimal solution to carry out image identification and classification. The method only comprises matrix multiplication, so that the method can be well compatible with a GPU (Graphics Processing Unit), a higher recognition speed is achieved, regular constraints of square root, low rank and sparsity can be effectively carried out on bilinear image expression at the same time, and the recognition accuracy is greatly improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a fine-grained image recognition method based on multi-objective Lagrangian regularization. Background technique [0002] Bilinear pooling operation has been widely used in fine-grained image recognition. The current method demonstrates that matrix square root regularization is effective in stabilizing high-order semantic information in bilinear representations. However, matrix square root regularization cannot solve the problems of information redundancy and weak generalization ability in bilinear features, which leads to the low recognition rate of current technology. Therefore, for the problem of fine-grained image recognition, we need a regularization technology that can efficiently and quickly stabilize high-level information, eliminate redundant information, and improve generalization ability to improve recognition accuracy. Contents of the invention [0003] The purp...

AI Technical Summary

Problems solved by technology

However, the matrix square root regularization cannot solve the problems of information redundancy and weak generalization ability in bilinear features, which leads to the low recognition rate of the current technology.

Images