Object detection model training method and device, object detection method and device, computer equipment and storage medium

Abstract

The invention relates to an object detection model training method and device, an object detection method and device, computer equipment and a storage medium. The object detection model training method comprises the steps of inputting an unlabeled first sample graph into an initial detection model of this round, and outputting a first prediction result for a target object; transforming a first prediction position area of the target object in the first sample graph and the first prediction result to obtain a second sample graph and a prediction transformation result of the target object in thesecond sample graph; inputting the second sample graph into the initial detection model, and outputting a second prediction result of the target object; obtaining a loss value of unsupervised learningaccording to the difference between the second prediction result and the prediction transformation result; and adjusting model parameters of the initial detection model according to the loss value, taking the next round as the current round, and returning to the step of inputting the first sample graph into the initial detection model of the current round to carry out iterative training until a training ending condition is met, thereby obtaining the object detection model. According to the scheme, the cost can be saved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence and machine learning, in particular to an object detection model training and object detection method, device, computer equipment and storage medium. Background technique [0002] With the rapid development of science and technology, artificial intelligence technology is getting more and more attention. Especially the application of machine learning technology in artificial intelligence technology is very extensive. A machine learning model capable of locating and identifying objects of interest can often be trained using machine learning techniques. For example, using medical images as samples, machine learning techniques are used to train object detection models to identify target objects in medical images. [0003] Supervised learning is a traditional approach to model training. However, for supervised learning methods, it is necessary to manually add a large amount o...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to provide an object detection model training method, device...

Images