Attention fine-grained classification method based on weak supervision position positioning
A classification method and attention technology, applied in the field of image classification, can solve the problems of time-consuming and laborious, difficult, unfavorable application, etc., and achieve the effect of reducing size, strengthening recognition ability, and considerable competitiveness.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0054] like Figure 1 to Figure 3 As shown in the figure, a fine-grained classification method of attention based on weakly supervised position location, specifically includes the following steps:
[0055] 101) Preprocessing step: constructing an initial object detection model, and extracting position information (x, y, l), size and semantic score in the model to prepare for the subsequent visual attention model;
[0056] The specific implementation of preprocessing is as follows:
[0057] When building the initial object detection model, the data in the training phase needs to be augmented, and the data augmentation includes horizontal / vertical flipping, translation, and scale variance. The initial network is trained using the SGD optimizer. The initial learning rate is 0.001, following a polynomial decay strategy with a weight decay of 0.0001. The batch size in the experiments is 8.
[0058] The object detection model consists of ResNet-50. The input data of the model co...
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