Image detection model training method and device and image detection method and device

Abstract

The invention relates to an image detection model training and image detection method and device, and the method comprises the steps: carrying out the training of an initial detection model through aninitial training set, and obtaining a first detection model; processing the second training sample through the first detection model to obtain a detection result of the second training sample; and training the first detection model through an extended training set comprising the first training sample and the second training sample to obtain a second detection model. According to the embodiment ofthe invention, the second training sample is detected through the first detection model, the detection result of the second training sample is obtained, and the detection result reduces the annotation workload. Furthermore, the training set is expanded through the second training sample and the labeling information thereof, the expanded training set is used for training the first detection modelto obtain the second detection model, the performance of the second detection model is improved, and the use scene of the second detection model is expanded.

Description

technical field [0001] The present disclosure relates to the field of computer technology, in particular to an image detection model training and image detection method and device. Background technique [0002] Recently, deep learning techniques have been widely used in image detection. However, the deep learning-based model needs to use a large amount of training data to train the model before it is put into practical application, so as to ensure the processing performance of the model in complex scenarios. Therefore, the demand for image training data in practical engineering is huge. Annotators need to annotate a large number of given pictures, and the workload of annotation is heavy, especially in the face of complex scenes, it is difficult to form a large-scale training set, which limits the usage scenarios and performance of the model. Contents of the invention [0003] The disclosure proposes a training method for an image detection model and an image detection me...

AI Technical Summary

Problems solved by technology

Annotators need to label a large number of given pictures, and the workload of labeling is heavy, especially in the face of complex scenes, it is difficult to form a large-scale training set, which limits the usage scenarios and performance of the model

Images