18431458. METHODS AND APPARATUS FOR DISCRIMINATIVE SEMANTIC TRANSFER AND PHYSICS-INSPIRED OPTIMIZATION OF FEATURES IN DEEP LEARNING simplified abstract (Intel Corporation)
Contents
- 1 METHODS AND APPARATUS FOR DISCRIMINATIVE SEMANTIC TRANSFER AND PHYSICS-INSPIRED OPTIMIZATION OF FEATURES IN DEEP LEARNING
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHODS AND APPARATUS FOR DISCRIMINATIVE SEMANTIC TRANSFER AND PHYSICS-INSPIRED OPTIMIZATION OF FEATURES IN DEEP LEARNING - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
METHODS AND APPARATUS FOR DISCRIMINATIVE SEMANTIC TRANSFER AND PHYSICS-INSPIRED OPTIMIZATION OF FEATURES IN DEEP LEARNING
Organization Name
Inventor(s)
METHODS AND APPARATUS FOR DISCRIMINATIVE SEMANTIC TRANSFER AND PHYSICS-INSPIRED OPTIMIZATION OF FEATURES IN DEEP LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18431458 titled 'METHODS AND APPARATUS FOR DISCRIMINATIVE SEMANTIC TRANSFER AND PHYSICS-INSPIRED OPTIMIZATION OF FEATURES IN DEEP LEARNING
Simplified Explanation
The patent application describes methods and apparatus for discriminative semantic transfer and physics-inspired optimization in deep learning.
- A computation training method for a convolutional neural network (CNN) involves receiving a sequence of training images in the CNN to describe objects of a cluttered scene as a semantic segmentation mask.
- The semantic segmentation mask is then received in a semantic segmentation network to produce semantic features.
- By using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.
Potential Applications
This technology could be applied in various fields such as image recognition, autonomous driving, robotics, and medical imaging.
Problems Solved
This technology helps in accurately identifying objects in cluttered scenes, improving the performance of deep learning models in complex environments.
Benefits
The benefits of this technology include enhanced object recognition, improved accuracy in semantic segmentation, and better understanding of cluttered scenes.
Potential Commercial Applications
Potential commercial applications of this technology include developing advanced surveillance systems, autonomous vehicles, medical diagnostic tools, and industrial automation solutions.
Possible Prior Art
One possible prior art for this technology could be the use of semantic segmentation in deep learning models for object recognition in images.
Unanswered Questions
How does this technology compare to existing methods for semantic segmentation in deep learning models?
This article does not provide a direct comparison with existing methods for semantic segmentation in deep learning models.
What are the limitations of this technology in real-world applications?
The article does not address the potential limitations of this technology in real-world applications.
Original Abstract Submitted
Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.