The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Apr. 20, 2021

Filed:

Jul. 23, 2018
Applicant:

Robert Bosch Gmbh, Stuttgart, DE;

Inventors:

Bilal Alsallakh, Mountain View, CA (US);

Amin Jourabloo, East Lansing, MI (US);

Mao Ye, San Jose, CA (US);

Xiaoming Liu, San Jose, CA (US);

Liu Ren, Cupertino, CA (US);

Assignee:

Robert Bosch GmbH, Stuttgart, DE;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06F 16/904 (2019.01); G06F 16/583 (2019.01); G06N 3/04 (2006.01); G06K 9/62 (2006.01); G06K 9/46 (2006.01); G06F 3/0484 (2013.01); G06N 3/08 (2006.01); G06N 5/04 (2006.01);
U.S. Cl.
CPC ...
G06F 16/904 (2019.01); G06F 3/04842 (2013.01); G06F 16/583 (2019.01); G06F 16/5838 (2019.01); G06K 9/4628 (2013.01); G06K 9/628 (2013.01); G06K 9/6262 (2013.01); G06K 9/6271 (2013.01); G06N 3/0454 (2013.01); G06N 3/084 (2013.01); G06N 5/046 (2013.01); G06N 3/0481 (2013.01);
Abstract

A visual analytics method and system is disclosed for visualizing an operation of an image classification model having at least one convolutional neural network layer. The image classification model classifies sample images into one of a predefined set of possible classes. The visual analytics method determines a unified ordering of the predefined set of possible classes based on a similarity hierarchy such that classes that are similar to one another are clustered together in the unified ordering. The visual analytics method displays various graphical depictions, including a class hierarchy viewer, a confusion matrix, and a response map. In each case, the elements of the graphical depictions are arranged in accordance with the unified ordering. Using the method, a user a better able to understand the training process of the model, diagnose the separation power of the different feature detectors of the model, and improve the architecture of the model.


Find Patent Forward Citations

Loading…