Implementation method of unsupervised domain adaptive model based on label correction
A technology of self-adaptive model and implementation method, which is applied in the direction of neural learning method, biological neural network model, character and pattern recognition, etc., which can solve the problem of ineffective usage and achieve the effect of improving training accuracy and efficiency and wide application prospects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment
[0060] Table 1: Office-31 dataset model simplified experimental classification accuracy (unit: %)
[0061]
[0062] The model simplification experiment refers to deleting a setting based on the complete experimental setting, and verifying the effectiveness of the setting by controlling variables; in order to ensure the accuracy and reliability of the experimental results, the experimental settings of all experiments are the same, except that the RevGrad method uses the original paper data In addition, the others are trained three times and calculate the variance; the six tasks in this experiment are composed of three sub-datasets in the Office-31 dataset, for example, A→W means the task of migrating the Amazon dataset to the Webcam dataset; each One row gives the performance of a specific method on each task, and the last column gives the average performance of a specific method on all tasks. The bold numbers in the table indicate that a specific task performs best in a cert...
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