Image fine-grained recognition method based on reinforcement learning strategy

Abstract

The invention provides a fine-grained recognition method based on reinforcement learning and cross bilinear features, aiming at solving the problem that an area with the best discrimination capabilityof a fine-grained image is difficult to mine. An actor-Critic strategy is used to mine the most attention-grabbing areas of an image. An Actor module is responsible for generating top M candidate areas with the best discrimination capability. A Critic module evaluates the state value of the action by utilizing the cross bilinear characteristic; and then calculates a reward value of the action under the current state by utilizing a sorting one-type reward, further obtains a value advantage, feeds the value advantage back to the Actor module, updates the output of the region with the most attention, and finally predicts the fine-grained category by using the region with the most discrimination capability in combination with the original image characteristics. According to the method, the region with the most attention of the fine-grained image can be better mined. It is verified by experiments that the recognition accuracy of the present invention on the CUB-200-2011 public data set isimproved compared with the existing methods, and the high fine-grain recognition accuracy rate is achieved respectively.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and multimedia signal processing, in particular to an image fine-grained recognition method based on a reinforcement learning strategy. Background technique [0002] With the continuous development of deep convolutional neural networks (CNN, Convolutional Central Networks), deep learning and other technologies have continuously improved the accuracy and reasoning efficiency of tasks such as target detection, semantic segmentation, target tracking and image classification in computer vision. It is due to the powerful nonlinear modeling capabilities of the convolutional neural network, 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 in the recognition...

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