公开(公告)号：US20240135722A1

公开(公告)日：2024-04-25

申请号：US18165857

申请日：2023-02-07

Applicant: NavInfo Europe B.V.

Inventor： Deepan Chakravarthi Padmanabhan ,  Shruthi Gowda ,  Elahe Arani ,  Bahram Zonooz

IPC: G06V20/58 ,  G06V10/82 ,  G06V20/40

CPC classification number: G06V20/58 ,  G06V10/82 ,  G06V20/41 ,  G06V2201/07

Abstract: A computer-implemented method that provides a novel shape aware FSL framework, referred to as LSFSL. In addition to the inductive biases associated with deep learning models, the method of the current invention introduces meaningful shape bias. The method of the current invention comprises the step of capturing the human behavior of recognizing objects by utilizing shape information. The shape information is distilled to address the texture bias of CNN-based models. During training, the model has two branches: RIN-branch, network with colored images as input, preferably RGB images, and SIN-branch, network with shape semantic-based input. Each branch incorporates a CNN backbone followed by a fully connected layer performing classification. RIN-branch and SIN-branch receive the RGB input image and shape information enhanced RGB input image, respectively. The training objective is to improve the classification performance of the RIN-branch and SIN-branch as well as to distill shape semantics from SIN-branch to RIN-branch. The features of the RIN-branch and SIN-branch are aligned to distill shape representation into RIN-branch. This feature alignment implicitly achieves a bias-alignment between the RIN and SIN. The learned representations are generic and remain invariant to common attributes.