Small sample target detection method for structured filter learning

Abstract

The invention discloses a small sample target detection method for structured filter learning, and the method comprises the following steps: preparing a small sample target detection data set and a base class target detection data set, and building a network structure; the backbone feature extraction network uses CSPDarknet53, and a general feature enhancement module is introduced; constructing a small sample target detection deep neural network learned by a structured filter; training the network by using the base class data set; on a small sample target detection data set, using a KSVD algorithm to hierarchically learn a dictionary of an input feature map of the structured filter, using the dictionary as a weight parameter of the filter, and completing initialization of the parameters of the structured filter through a forward propagation process; continuously training on the small sample data set by using the initialized network model; and completing a detection task by using the trained neural network. According to the method, the target detection deep neural network with good generalization performance can be trained only through a small amount of sample data.

Description

technical field [0001] The invention belongs to the field of small sample target detection, in particular to a small sample target detection method for structured filter learning. Background technique [0002] Computer vision is a very popular research field of artificial intelligence. In today's information society, a large amount of visual information such as pictures and videos needs to be processed and applied every day. Research in the field of computer vision has become particularly necessary and urgent. It is an important branch of computer vision. The main task of target detection is to frame one or more specific object targets in a digital image and give the confidence of the category to which the target belongs. As one of the most fundamental problems in the field of computer vision technology, object detection is the foundation and prerequisite for many other advanced computer vision tasks, such as image segmentation, image understanding, object tracking, and int...

AI Technical Summary

Problems solved by technology

[0003] Although deep learning has surpassed humans in many fields, deep learning needs to learn a large number of samples if it wants to make achievements in a new field. In contrast, human learning is particularly simple and efficient. Only one Human beings can distinguish this person from the crowd by taking photos. It is very difficult to complete such a task with deep learning. However, there are a large number of similar problems in the real world. Most of the problems faced by deep learning are not Without a sufficient amount of data, such as failure data in industrial production, characteristic data of new molecules in drug development, etc., the collection of data itself requires high costs; there are still a considerable number of tasks due to ethical issues or privacy, security and other issues. It does not have the conditions to obtain a large number of samples. In many cases, even if there are sufficient samples, it will take a lot of manpower and material resources to label these data in advance, which is time-consuming and labor-intensive.

Images