Target identification model training and target identification method and device, and computing equipment

Abstract

The invention discloses a target identification model training method, a target identification model training device, a target identification method, a target identification device and computing equipment, which belong to the technical field of computer vision. The target identification model training method comprises the steps of: inputting a plurality of local candidate regions selected for a training image into a target identification model, so as to obtain a preliminary result of classification of the plurality of local candidate regions output by the target identification model; performing local candidate region integration according to weak supervisory information and the preliminary result of classification of the plurality of local candidate regions; correcting parameters of the target identification model according to the preliminary result of classification of the plurality of local candidate regions and a result of local candidate region integration; and iteratively executing the training steps till a training result of the target identification model satisfies a predetermined convergence condition. The target identification model training method, the target identification model training device, the target identification method, the target identification device and the computing equipment can perform direct supervision of pixel level, can optimize a semantic segmentation model in an end-to-end manner, and can improve the result of target identification according to judgment of the local candidate regions.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a target recognition model training and target recognition method and device, and computing equipment. Background technique [0002] Object recognition is a classic problem in the field of computer vision, where the purpose is to predict the location of a given object in an input image. A good object recognition scheme relies on the object category of each pixel to achieve accurate and dense image pixel-level understanding. The object recognition problem is usually very time-consuming because of the need to label the positions of all objects in the image. According to the practical experience of common methods, it usually takes 5-8 minutes to obtain an accurate target recognition label with a size of 400*600 pixels. Therefore, the speed and quality of data annotation has become an important issue that restricts the problem from obtaining big data support and further dev...

AI Technical Summary

Problems solved by technology

The target recognition problem is usually very time-consuming because it is necessary to label the positions of all objects in the image

According to the practical experience of common methods, it usually takes 5-8 minutes to obtain an accurate target recognition label with a size of 400*600 pixels

Images