18377649. ELECTRONIC DEVICE FOR IMPROVING THE EXPLAINABILITY OF SATELLITE IMAGE simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
Contents
- 1 ELECTRONIC DEVICE FOR IMPROVING THE EXPLAINABILITY OF SATELLITE IMAGE
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 ELECTRONIC DEVICE FOR IMPROVING THE EXPLAINABILITY OF SATELLITE IMAGE - 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
ELECTRONIC DEVICE FOR IMPROVING THE EXPLAINABILITY OF SATELLITE IMAGE
Organization Name
Inventor(s)
Chan-Hyun Youn of Daejeon (KR)
ELECTRONIC DEVICE FOR IMPROVING THE EXPLAINABILITY OF SATELLITE IMAGE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18377649 titled 'ELECTRONIC DEVICE FOR IMPROVING THE EXPLAINABILITY OF SATELLITE IMAGE
Simplified Explanation
The patent application describes an electronic device that utilizes artificial intelligence models to process data and output classification results.
- The device inputs data to a first artificial intelligence model with convolution blocks and pooling layers, then passes the resulting feature maps to a second model with local attention blocks to generate attention maps.
- The device amplifies a region in the feature maps based on the attention maps to create an amplified feature map, which is then input to a classifier for classification.
- The device ultimately outputs a classification result for the input data.
Potential Applications
This technology can be applied in various fields such as image recognition, natural language processing, and medical diagnosis where classification tasks are required.
Problems Solved
This technology helps improve the accuracy and efficiency of classification tasks by utilizing artificial intelligence models with convolution and attention mechanisms.
Benefits
The benefits of this technology include enhanced classification accuracy, faster processing speeds, and the ability to handle complex data patterns effectively.
Potential Commercial Applications
Potential commercial applications of this technology include automated image recognition systems, intelligent virtual assistants, and medical diagnostic tools.
Possible Prior Art
One possible prior art for this technology could be the use of convolutional neural networks and attention mechanisms in artificial intelligence models for classification tasks.
What are the specific technical details of the convolution blocks and local attention blocks used in the artificial intelligence models described in the patent application?
The specific technical details of the convolution blocks and local attention blocks, such as the number of layers, filter sizes, activation functions, and attention mechanisms, are not provided in the abstract of the patent application.
How does the device handle input data preprocessing before feeding it into the artificial intelligence models?
The abstract does not mention the specific details of how the device handles input data preprocessing before feeding it into the artificial intelligence models.
Original Abstract Submitted
An electronic device includes a memory configured to store at least one instruction; and at least one processor configured to execute the at least one instruction to: input first data to a first artificial intelligence model including a plurality of convolution blocks sequentially connected with a pooling layer interposed therebetween to obtain a plurality of feature maps that are output by corresponding ones of the plurality of convolution blocks, input the first data and the plurality of feature maps to a second artificial intelligence model including a plurality of local attention blocks sequentially connected to obtain a plurality of attention maps that are output by corresponding ones of the plurality of local attention blocks, output an amplified feature map by amplifying a region corresponding to a last attention map among the plurality of attention maps in a last feature map among the plurality of feature maps, and input the amplified feature map to a classifier to output a classification result for the first data.
