Intellectual Property India Publishes Patent Application for 'Automatically Quantifying A Robustness Of An Object Detection Model Applied For A Controlling Task And/Or A Monitoring Task' Filed by Siemens Aktiengesellschaft

MUMBAI, India, Aug. 22 -- Intellectual Property India has published a patent application (202517072885 A) filed by Siemens Aktiengesellschaft, Munchen, Germany, on July 31, for 'automatically quantifying a robustness of an object detection model applied for a controlling task and/or a monitoring task.'

Inventor(s) include Buttner, Florian; and Yang, Yinchong.

The application for the patent was published on Aug. 22, under issue no. 34/2025.

According to the abstract released by the Intellectual Property India: "Computer-implemented method for automatically quantifying a robustness of an object detection model (f) applied for a controlling task and/or a monitoring task, comprising - receiving (S1) the object detection model (f) which is trained to output a predicted object in terms of a location in an image data (x) and of an object class out of a set of object classes when the image data (x) is input into the object detection model (f), - applying (S2) a set of robustness requirements to the ob-ject detection model (f), - deriving (S3) from each robustness requirement a cross Lipschitz-ness function (g), which quantifies the robustness requirement conditioned on the object detection model (f) for the input image data (x), - determining (S4) a robustness value (RV) of the object detection model (f) by calculating the cross Lipschitz-ness function integrated into a Cross Lipschitz Extreme Value for Network Robustness CLEVER score of the object detection model (f) for a perturbed image data (xp) deviating from the unperturbed image data (x0) of the image data (x), - comparing (S5) the determined robustness value (RV) with a predefined robustness threshold value (RT), and - outputting (S6) a positive certification (C) for applying the object detection model (f) in the controlling task and/or the monitoring task if the robustness value (RV) is below the predefined robustness threshold value (RT)."

The patent application was internationally filed on Feb. 02, 2024, under International application No.PCT/EP2024/052641.

Disclaimer: Curated by HT Syndication.