View source for Samsung electronics co., ltd. (20240135682). ELECTRONIC DEVICE FOR IMPROVING THE EXPLAINABILITY OF SATELLITE IMAGE simplified abstract

=ELECTRONIC DEVICE FOR IMPROVING THE EXPLAINABILITY OF SATELLITE IMAGE=


==Organization Name==

[[:Category:samsung electronics co., ltd.|samsung electronics co., ltd.]]


[[Category:samsung electronics co., ltd.]]

==Inventor(s)==

[[:Category:Chan-Hyun Youn of Daejeon (KR)|Chan-Hyun Youn of Daejeon (KR)]][[Category:Chan-Hyun Youn of Daejeon (KR)]]

[[:Category:Taewoo Kim of Daejeon (KR)|Taewoo Kim of Daejeon (KR)]][[Category:Taewoo Kim of Daejeon (KR)]]

[[:Category:Changha Lee of Daejeon (KR)|Changha Lee of Daejeon (KR)]][[Category:Changha Lee of Daejeon (KR)]]

[[:Category:Minsu Jeon of Daejeon (KR)|Minsu Jeon of Daejeon (KR)]][[Category:Minsu Jeon 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 20240135682 titled 'ELECTRONIC DEVICE FOR IMPROVING THE EXPLAINABILITY OF SATELLITE IMAGE

==Simplified Explanation==

The abstract describes an electronic device that utilizes artificial intelligence models to process data and output a classification result. The device includes a memory and at least one processor to execute instructions for inputting data to convolution and attention models, amplifying feature maps, and classifying the data.

* The electronic device includes a memory and processor to execute instructions for processing data using artificial intelligence models.
* The device inputs data to convolution and attention models to obtain feature maps and attention maps.
* It amplifies feature maps based on attention maps to enhance specific regions.
* The device then classifies the data using a classifier to output a classification result.

== Potential Applications ==
This technology can be applied in various fields such as image recognition, natural language processing, and medical diagnosis.

== Problems Solved ==
This technology helps in improving the accuracy and efficiency of classification tasks by utilizing artificial intelligence models.

== Benefits ==
The benefits of this technology include enhanced data processing capabilities, improved classification accuracy, and potential for automation in various industries.

== Potential Commercial Applications ==
One potential commercial application of this technology could be in the development of advanced security systems for image and voice recognition.

== Possible Prior Art ==
Prior art in this field may include research papers or patents related to artificial intelligence models for data processing and classification tasks.

=== What are the specific artificial intelligence models used in this technology? ===

The abstract mentions the use of convolution and attention models, but it does not provide detailed information on the specific architecture or algorithms employed in these models.

=== How does the device handle input data that is complex or noisy? ===

The abstract does not address how the device processes complex or noisy input data to ensure accurate classification results.


==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.



[[Category:G06V10/771]]
[[Category:G06V10/764]]
[[Category:G06V20/13]]