公开(公告)号：US20210166347A1

公开(公告)日：2021-06-03

申请号：US17107283

申请日：2020-11-30

Applicant: NavInfo Europe B.V.

Inventor： Elahe Arani ,  Shabbir Marzban ,  Andrei Pata ,  Bahram Zonooz

IPC: G06T3/40 ,  G06T9/00 ,  G06T5/30

Abstract: A semantic segmentation architecture comprising an asymmetric encoder-decoder structure, wherein the architecture comprises further an adapter for linking different stages of the encoder and the decoder. The adapter amalgamates information from both the encoder and the decoder for preserving and refining information between multiple levels of the encoder and decoder. In this way the adapter aggregates features from different levels and intermediates between encoder and decoder.

公开(公告)号：US12147502B2

公开(公告)日：2024-11-19

申请号：US17502729

申请日：2021-10-15

Applicant: NavInfo Europe B.V.

Inventor： Elahe Arani ,  Vijaya Raghavan Thiruvengadathan Ramkumar ,  Bahram Zonooz

IPC: G06F18/214 ,  G06F18/213 ,  G06F18/22 ,  G06N20/00 ,  G06V10/70 ,  G06V10/94 ,  G06V20/00

Abstract: A computer implemented network for executing a self-supervised scene change detection method, wherein at least one image pair with images captured at different instances of time is processed to detect structural changes caused by an appearance or disappearance of an object in the image pair, and wherein a self-supervised pretraining method is employed that utilizes an unlabelled image pair or pairs to learn representations for scene change detection, and wherein the aligned image pair is subjected to a differencing based self-supervised pre-training method to maximize a correlation between changed regions in the images which provide the structural changes that occur in the image pairs.

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.

公开(公告)号：US20240127066A1

公开(公告)日：2024-04-18

申请号：US18161312

申请日：2023-01-30

Applicant: NavInfo Europe B.V.

Inventor： Vijaya Raghavan Thiruvengadathan Ramkumar ,  Elahe Arani ,  Bahram Zonooz

IPC: G06N3/082 ,  G06N3/04

CPC classification number: G06N3/082 ,  G06N3/04

Abstract: A computer-implemented method for improving generalization in training deep neural networks in online settings. The method includes a general learning paradigm for sequential data that is referred to as Learn, Unlearn, RElearn (LURE), a dynamic re-initialization method to address the above-mentioned larger problem of generalization of parameterized networks on sequential data by selectively retaining the task-specific connections through the important criteria and re-randomizing the less important parameters at each mega batch of training. The method of selectively forgetting retains previous information all the while improving generalization to unseen samples.

公开(公告)号：US20240119280A1

公开(公告)日：2024-04-11

申请号：US18157476

申请日：2023-01-20

Applicant: NavInfo Europe B.V.

Inventor： Fahad Sarfraz ,  Elahe Arani ,  Bahram Zonooz

IPC: G06N3/08 ,  G06F18/21 ,  G06F18/2113

CPC classification number: G06N3/08 ,  G06F18/2113 ,  G06F18/217

Abstract: A computer-implemented method that maintains a memory of errors along the training trajectory and adjusts the contribution of each sample towards learning based on how far it is from the mean statistics of the error memory. The method may include the step of maintaining an additional semantic memory, called a stable model, which gradually aggregates the knowledge encoded in the weights of the working model. The stable model is utilized to select the low loss samples from the current task for populating the error memory. The different components of the method complement each other to effectively reduce the drift in representations at the task boundary and enables consolidation of information across the tasks.

公开(公告)号：US20240028885A1

公开(公告)日：2024-01-25

申请号：US17894870

申请日：2022-08-24

Applicant: NavInfo Europe B.V.

Inventor： Shruthi Gowda ,  Bahram Zonooz ,  Elahe Arani

IPC: G06N3/08 ,  G06N3/04 ,  G06T7/13 ,  G06V10/74

CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06T7/13 ,  G06V10/761 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A computer-implemented method of self-supervised learning for deep neural networks including the steps of: providing input images (x); extracting implicit shape information from the input images; and performing self-supervised learning on at least two deep neural network (f) based on the provided input images (x) and the at least one extracted implicit shape information for enabling said at least one deep neural network (f) to classify and/or detect objects within other input images.

公开(公告)号：US11847802B2

公开(公告)日：2023-12-19

申请号：US17234444

申请日：2021-04-19

Applicant: NavInfo Europe B.V.

Inventor： Hemang Chawla ,  Matti Jukola ,  Terence Brouns ,  Elahe Arani ,  Bahram Zonooz

IPC: G06V20/20 ,  G06T7/50 ,  G06F16/587

CPC classification number: G06V20/20 ,  G06F16/587 ,  G06T7/50

Abstract: Systems arranged to implement methods for positioning a semantic landmark in an image from the real world during a continuous motion of a monocular camera providing said image, using in combination image information from the camera and GPS information, wherein the camera parameters are unknown a priori and are estimated in a self-calibration step, wherein in a subsequent step positioning of the landmarks is completed using one of camera ego motion and depth estimation.

公开(公告)号：US11842532B2

公开(公告)日：2023-12-12

申请号：US17970888

申请日：2022-10-21

Applicant: NavInfo Europe B.V.

Inventor： Elahe Arani ,  Shabbir Marzban ,  Andrei Pata ,  Bahram Zonooz

IPC: G06V10/82 ,  G06T7/11 ,  G06V10/764 ,  G06N3/084

CPC classification number: G06V10/82 ,  G06T7/11 ,  G06V10/764 ,  G06N3/084 ,  G06T2207/20016 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A semantic segmentation architecture comprising an asymmetric encoder—decoder structure, wherein the architecture comprises further an adapter for linking different stages of the encoder and the decoder. The adapter amalgamates information from both the encoder and the decoder for preserving and refining information between multiple levels of the encoder and decoder. In this way the adapter aggregates features from different levels and intermediates between encoder and decoder.

公开(公告)号：US20230281438A1

公开(公告)日：2023-09-07

申请号：US17686276

申请日：2022-03-03

Applicant: NavInfo Europe B.V.

Inventor： Prashant Shivaram Bhat ,  Elahe Arani ,  Bahram Zonooz

IPC: G06N3/08 ,  G06N3/10

CPC classification number: G06N3/08 ,  G06N3/10

Abstract: A deep learning framework in continual learning that enforces consistency in predictions across time separated views and enables learning rich discriminative features for mitigating catastrophic forgetting in low buffer regimes. A deep-learning based computer-implemented method for continual learning over non-stationary data streams involves a number of sequential tasks (T) in which for each task (t) the method includes the steps of training a classification head with an objective function based on experience replay; and casting consistency regularization as an auxiliary self-supervised pretext-task.

公开(公告)号：US20230114762A1

公开(公告)日：2023-04-13

申请号：US17970888

申请日：2022-10-21

Applicant: NavInfo Europe B.V.

Inventor： Elahe Arani ,  Shabbir Marzban ,  Andrei Pata ,  Bahram Zonooz

IPC: G06T7/11 ,  G06V10/82

Abstract: A semantic segmentation architecture comprising an asymmetric encoder—decoder structure, wherein the architecture comprises further an adapter for linking different stages of the encoder and the decoder. The adapter amalgamates information from both the encoder and the decoder for preserving and refining information between multiple levels of the encoder and decoder. In this way the adapter aggregates features from different levels and intermediates between encoder and decoder.