Zero-sample image recognition algorithm and system based on auto-encoder
A self-encoder and sample image technology, applied in the field of image recognition, can solve problems such as inaccurate prediction of unknown sample attributes
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0122] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0123] While training effective sample features from the source domain, how to use the source domain sample features to accurately predict the attributes of unknown samples, so as to perform image recognition based on the predicted sample attributes, the present invention provides a zero-sample autoencoder-based Image recognition algorithm and system. refer to figure 1 As shown in , it is a schematic flowchart of an autoencoder-based zero-shot image recognition algorithm provided by an embodiment of the present invention.
[0124] In this embodiment, the zero-shot image recognition algorithm based on an autoencoder includes:
[0125] S1. Use the pre-trained Arc-SENet network to extract feature vectors of known class samples in the source domain.
[0126] First, the present invention selects image samples of known c...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com