US Patent Application 18142997. METHODS AND APPARATUS FOR DISCRIMINATIVE SEMANTIC TRANSFER AND PHYSICS-INSPIRED OPTIMIZATION OF FEATURES IN DEEP LEARNING simplified abstract

From WikiPatents
Jump to navigation Jump to search

METHODS AND APPARATUS FOR DISCRIMINATIVE SEMANTIC TRANSFER AND PHYSICS-INSPIRED OPTIMIZATION OF FEATURES IN DEEP LEARNING

Organization Name

Intel Corporation


Inventor(s)

Anbang Yao of Beijing (CN)

Hao Zhao of Beijing (CN)

Ming Lu of Beijing (CN)

Yiwen Guo of Beijing (CN)

Yurong Chen of Beijing (CN)

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 18142997 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 improving deep learning algorithms by combining discriminative semantic transfer and physics-inspired optimization techniques.

  • The method involves training a convolutional neural network (CNN) using a sequence of training images.
  • The CNN is divided into two stages: the first stage receives the training images and generates a semantic segmentation mask to describe objects in a cluttered scene.
  • The second stage receives the semantic segmentation mask and produces semantic features.
  • The weights from the first stage are used as feature extractors, while the weights from the second stage act as classifiers.
  • By utilizing these weights, the algorithm can identify edges in the cluttered scene using the semantic features.
  • The combination of discriminative semantic transfer and physics-inspired optimization helps improve the accuracy and efficiency of deep learning algorithms.


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.

Retrieved from "http://wikipatents.org/index.php?title=US_Patent_Application_18142997._METHODS_AND_APPARATUS_FOR_DISCRIMINATIVE_SEMANTIC_TRANSFER_AND_PHYSICS-INSPIRED_OPTIMIZATION_OF_FEATURES_IN_DEEP_LEARNING_simplified_abstract&oldid=7142"