Zero-sample target detection system and learnable semantic and fixed semantic fusion method

Abstract

The invention discloses a zero-sample target detection system and a learnable semantic and fixed semantic fusion method, a zero-sample learning mechanism is introduced into a deep target detection framework, a set of zero-sample target detection system LATNet with strong discrimination capability is established, and an end-to-end zero-sample target detection task is realized through the LATNet. Alearnable semantic feature and fixed semantic feature combined method is used, so that when a network is trained in a source domain, word vector information of a category can be fully utilized, end-to-end learning can also be utilized, a category prototype with better identification capability is discovered, and the best detection accuracy is obtained. The system is simple in framework, convenientto use, high in expandability and high in interpretability, and the results of the two tasks of zero sample detection and generalized zero sample detection of the two mainstream visual attribute datasets exceed those of an existing method. And the support of a basic framework and a method is provided for the target detection technology in the military and industrial application fields.

Description

technical field [0001] The present application relates to the technical field of machine learning, in particular to a zero-sample object detection system and a fusion method of learnable semantics and fixed semantics. Background technique [0002] Target detection technology is a basic task in computer vision tasks, which aims to locate and classify target category objects from images. Target detection technology has a wide range of applications, and it provides basic support for some downstream tasks, such as instance segmentation, scene understanding, pose estimation and other tasks. Existing deep object detection models have achieved good accuracy in some categories, but rely heavily on large-scale calibrated datasets. However, in real scenarios, we are faced with problems such as unbalanced distribution of data samples and unsupervised samples. Therefore, how to make full use of the data in social media when the sample size is insufficient or even zero samples, and the ...

AI Technical Summary

Problems solved by technology

[0009] In order to improve the accuracy of image target recognition using the zero-shot learning method, this application provides a zero-shot target detection system and a fusion method of learnable semantics and fixed semantics, which combines learnable semantic features and fixed semantic vectors for zero-shot target detection The algorithm, on the basis of retaining the existing visual-fixed semantic mapping module, adds a visual-learnable semantic mapping module in parallel, and synthesizes the output results of the two parts to complete the final prediction and solve the problems caused by fixed semantic features. Difficulty in neural network training and poor discrimination

Images