TARGET DETECTION METHOD, MODEL TRAINING METHOD, DEVICE, APPARATUS AND STORAGE MEDIUM

摘要

The present application discloses a target detection method, a model training method, a device, an apparatus and a storage medium. The target detection method includes: acquiring a first image to be detected, the first image to be detected belonging to a first domain; acquiring a second image to be detected corresponding to the first image to be detected, the second image to be detected belonging to a second domain; acquiring the detection result corresponding to the second image to be detected through a cross-domain image detection model, the detection result including target positioning information and target category information of the target object, the cross-domain image detection model including a first network model for transforming the image from the first domain to the second domain and a second network model for regional positioning of images in the second domain. The present application transforms the style of the image to be detected into the style of the test set image by the cross-domain image detection model, further performs target positioning on the transformed image, to improve the accuracy of image positioning and enhance the model prediction effect.