公开(公告)号：US20230196118A1

公开(公告)日：2023-06-22

申请号：US18066624

申请日：2022-12-15

Applicant: THALES CANADA INC.

Inventor： Simon CORBEIL-LETOURNEAU ,  Freddy LECUE ,  David BEACH

IPC: G06N3/091

CPC classification number: G06N3/091

Abstract: A method of improving robustness of a deep neural network (DNN), the method including: applying a coverage metric to a trained DNN based on a test set to determine test set adequacy; monitoring a performance of the trained DNN; based on the performance, applying new data to the trained DNN; applying a novelty metric to an output of the trained DNN based on the applied new data to identify a subset of the applied new data in response to determining whether new features are generated; and identifying the subset of the applied new data.

公开(公告)号：US20210264226A1

公开(公告)日：2021-08-26

申请号：US17184159

申请日：2021-02-24

Applicant: THALES CANADA INC.

Inventor： Freddy LECUE ,  David BEACH ,  Tanguy POMMELLET

IPC: G06K9/72 ,  G06N3/08 ,  G06N3/04 ,  G06F16/901

Abstract: A method of semantic object detection in an image dataset includes extracting semantic links relevant to the image dataset. Objects are detected in the image dataset and confidence scores are assigned to the detected objects. The semantic object detection compares the detected objects with the semantic links and augments the confidence scores based on the semantic links between the detected objects.

公开(公告)号：US20240153261A1

公开(公告)日：2024-05-09

申请号：US18546355

申请日：2022-02-11

Applicant: THALES CANADA INC.

Inventor： Ola AHMAD ,  Freddy LECUE

IPC: G06V10/82 ,  G06V10/44 ,  G06V10/75

CPC classification number: G06V10/82 ,  G06V10/454 ,  G06V10/76

Abstract: There is provided a method and system for training an object recognition machine learning model to perform object recognition in data acquired by ultrawide field of view (UW FOV) sensors to thereby obtain a distortion-aware object recognition model. The object recognition model comprises convolution layers each associated with a set of kernels. During training on a UW FOV labelled training dataset, deformable kernels are learned in a manifold space, mapped back to Euclidian space and used to perform convolutions to obtain output feature maps which are used to perform object recognition predictions. Model parameters of the distortion-aware object recognition model may be transferred to other architectures of object recognition models, which may be further compressed for deployment on embedded systems such as electronic devices on board autonomous vehicles.