Zero sample image classification method based on generative adversarial network
A technology of sample images and classification methods, applied in the field of deep learning, can solve the problems of single image features, collapse of adversarial network mode, low classification accuracy, etc., to achieve diversification of visual image features, improve classification accuracy, and close correlation. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0045] To make the objectives, technical solutions, and advantages of the present invention clearer, the following description of the present invention in detail in conjunction with accompanying drawings and specific embodiments.
[0046] The present invention provides a method of classification based on zero sample image generated against a network, characterized by generating a visual image of the unknown samples into classes so that the classification task to zero conventional image classification task, while, for generating network against network do generator an improved, it features a visual image generated more real, so as to further improve the quality of generated visual image features; then the image feature key information through visual attention network location of image features, ignoring other interference information, in order to train classifier, such that less information generator capable of generating a visual image feature interference; classification method o...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap