• Patent Title: Method for generating detailed visualization of machine learning model behavior
  • Application No.: US17302592
    Application Date: 2021-05-07
  • Publication No.: US11688112B2
    Publication Date: 2023-06-27
  • Inventor: Peter Doliwa
  • Applicant: NXP B.V.
  • Applicant Address: NL Eindhoven
  • Assignee: NXP B.V.
  • Current Assignee: NXP B.V.
  • Current Assignee Address: NL Eindhoven
  • Agent Daniel D. Hill
  • Main IPC: G06T11/20
  • IPC: G06T11/20 G06T3/40 G06N5/04 G06N20/00
Method for generating detailed visualization of machine learning model behavior
Abstract:
A method is provided for generating a visualization for explaining a behavior of a machine learning (ML) model, the method includes inputting an image into a machine learning (ML) model for an inference operation. A first heatmap is generated for the image using a first visualization method. An area of highest attention is selected on the first heatmap based a predetermined threshold. The selected area is cropped from the image. The cropped selected area is upscaled. A second heatmap is generated for the cropped and upscaled selected area of the image. A final visualization is presented for analysis. In another embodiment, a computer program comprising instructions for executing the method is provided.
Information query
Patent Agency Ranking
0/0