A bilinear feature fusion fine-grained concept model and a learning method

Abstract

The invention discloses a bilinear feature fused fine-grained concept model and a learning method. The method comprises the following steps: carrying out external product, pooling and other methods onmulti-layer features in a fine-grained image extracted by a deep convolutional network model vgg16 to obtain bilinear feature descriptors with discriminative local features, fusing the descriptors, and fusing the multi-window features extracted by the feature graphs fused with VGG-16conv5_1 path, the conv5_2 path and the conv5_3 path with bilinear features extracted by the VGG-16conv5_2 path andthe conv5_3 path and sending the data to a full connection layer, and then connecting the data with a softmax multi-class classifier to obtain a classification result. In the data preprocessing stage,input image data are preprocessed, the image mean value is subtracted to eliminate noise, and data enhancement means such as image random clipping and image horizontal overturning are effectively utilized. Under the condition that only the class information of the image level needs to be provided, the classification precision is improved through fine-grained image multi-layer feature fusion.

Description

technical field [0001] The invention belongs to the field of information technology, relates to pattern recognition and image processing technology, in particular to a fine-grained conceptual model and a learning method for bilinear feature fusion. Background technique [0002] Fine-grained image classification (Fine-Grained Categorization), also known as sub-category image classification (Sub-Category Recognition), is a very popular research topic in the fields of computer vision and pattern recognition in recent years. Its purpose is to carry out more fine-grained subcategories for coarse-grained large categories. The category accuracy of fine-grained images is more detailed, and the differences between categories are more subtle. Often, different categories can only be distinguished with the help of small local differences. Compared with object-level classification tasks such as face recognition, the intra-class differences of fine-grained images are even greater, and th...

AI Technical Summary

Problems solved by technology

However, this model only uses the features output by the single-channel VGG-16 model Conv5_3 for outer product, and the bilinear features obtained by pooling are sent to the final softmax classifier

The feature information of other layers in the network is lost, and the outer product operation is performed on two very high-dimensional (512-dimensional) vectors, and the algorithm complexity in the process is high

Images