Image fine-grain identification method based on multi-stream multi-scale cross bilinear features

Abstract

The invention provides an image fine-grain identification method based on multi-stream multi-scale cross bilinear features. Aiming at the problems of insufficient extraction and insufficient feature utilization of fine-grain features of the image, the image fine-grain identification method utilizes a multi-stream network to extract cross bilinear features, and the features can represent finer local features of the image, thus solving the problem of insufficient feature extraction. The image fine-grain identification method solves the problem of insufficient feature utilization by using a method for enhancing and fusing multi-scale bottom layer bilinear features through image random mixing. Experimental verification shows that the fine-grain identification method based on multi-stream network fused multi-scale cross bilinear features provided by the invention remarkably improves the identification accuracy on a CUB-200-2011 public data set, compared with an existing method, and achievesthe optimal fine-grain identification accuracy.

Description

technical field [0001] The invention relates to the fields of computer vision, artificial intelligence and multimedia signal processing, in particular to an image fine-grained recognition method based on multi-stream and multi-scale cross-bilinear features. Background technique [0002] With the continuous development of deep convolutional neural networks in cities, technologies such as deep learning have continuously improved the accuracy and reasoning efficiency of tasks such as object detection, semantic segmentation, object tracking, and image classification in computer vision, which is mainly due to the The powerful nonlinear modeling capabilities of convolutional neural networks, the current massive data and the improvement of the computing power of hardware devices. And this has also brought great development to the computer vision task of image fine-grained recognition. At present, the methods for image classification tasks are relatively mature, which is reflected ...

AI Technical Summary

Problems solved by technology

Therefore, the fine-grained recognition task has the characteristics of small variance between sub-categories and large variance within sub-categories. Compared with coarse-grained image recognition, fine-grained image sub-categories are easy to confuse, and there are fewer information areas that can be distinguished. There are many similar features between images, so the difficulty of fine-grained image recognition increases

Images