-
1.发明公开公开(公告)号：US20240054337A1
公开(公告)日：2024-02-15
申请号：US17902421
申请日：2022-09-02
Applicant: NavInfo Europe B.V.
Inventor： Kishaan Jeeveswaran , Prashant Shivaram Bhat , Elahe Arani , Bahram Zonooz
CPC classification number: G06N3/08 , G06N3/0454
Abstract: A computer-implemented method for continual task learning in a training framework. The method includes: providing a first deep neural network (θw) including a first function (Gw) and a second function (Fw) which are nested; providing a second deep neural network (θs) including a third function (Fs) as a counterpart to the second nested function (Fw); feeding input images to the first neural network (θw), such as through a filter and/or via patch embedding; generating representations of task samples using the first function (Gw); providing a memory (Dm) for storing at least some of the generated representations of task samples and/or having pre-stored task representation; providing the generated and memory stored representations of task samples to the second function (Fw); and providing memory stored representations of task samples to the third function (Fs).
-
2.发明公开公开(公告)号：US20230281451A1
公开(公告)日：2023-09-07
申请号：US17686263
申请日：2022-03-03
Applicant: NavInfo Europe B.V.
Inventor： Fahad Sarfraz , Elahe Arani , Bahram Zonooz
Abstract: A computer-implemented method of synaptic consolidation for training a neural network using an episodic memory, and a semantic memory, by using a Fisher information matrix for estimating the importance of each synapse in the network to previous tasks of the neural network; evaluating the Fisher information matrix on the episodic memory using the semantic memory; adjusting the importance estimate such that functional integrity of the filters in the convolutional layers is maintained whereby the importance of each filter is given by the mean importance of its parameters; using the weights of the semantic memory as the anchor parameters for constraining an update of the synapses of the network based on the adjusted importance estimate; updating the semantic memory and fisher information matrix stochastically using exponential moving average, and interleaving samples from a current task with samples from the episodic memory for performing the training.
-
公开(公告)号：US20230237785A1
公开(公告)日：2023-07-27
申请号：US17581759
申请日：2022-01-21
Applicant: NavInfo Europe B.V.
Inventor： Shruthi Gowda , Elahe Arani , Bahram Zonooz
CPC classification number: G06V10/82 , G06V10/7715 , G06N20/20
Abstract: A Deep Learning based Multi-sensor Detection System for executing a method to process images from a visual sensor and from a thermal sensor for detection of objects in said images, wherein a first deep learning network for processing images from the visual sensor and a second deep learning network for pro-cessing images from the thermal sensor are jointly used and collaboratively trained for improving both networks ability to accurately detect said objects in said images.
-
公开(公告)号：US20230123493A1
公开(公告)日：2023-04-20
申请号：US17502729
申请日：2021-10-15
Applicant: NavInfo Europe B.V.
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：US20240265684A1
公开(公告)日：2024-08-08
申请号：US18163792
申请日：2023-02-02
Applicant: NavInfo Europe B.V.
Inventor： Haris Iqbal , Elahe Arani , Bahram Zonooz
IPC: G06V10/774 , G06V10/764 , G06V10/82 , G06V20/58
CPC classification number: G06V10/7753 , G06V10/764 , G06V10/82 , G06V20/58
Abstract: A computer-implemented method for the detection and recognition of objects in unlabeled image data using an automated labelling architecture. The method includes the steps of: proposing bounding-box in every image of the unlabeled image data using a task specific and/or a related task pretrained object detection model and a Bounding Box Sampler module; filtering said bounding boxes for positive object instances; assigning to said filtered bounding boxes a class label using a Few-Shot Classification module; and modifying filtered bounding boxes based on additional class wise attention output from the Few-Shot Classification module.
-
Patent Agency Ranking
公开(公告)号：US20240046102A1
公开(公告)日：2024-02-08
申请号：US17900272
申请日：2022-08-31
Applicant: NavInfo Europe B.V.
Inventor： Fahad Sarfraz , Elahe Arani , Bahram Zonooz
CPC classification number: G06N3/084 , G06N3/0481
Abstract: A computer-implemented method for general continual learning (CL) in artificial neural network that provides a biologically plausible framework for continual learning which incorporates different mechanisms inspired by the brain. The underlying model comprises separate populations of exclusively excitatory and exclusively inhibitory neurons in each layer which adheres to Dale's principle and the excitatory neurons (mimicking pyramidal cells) are augmented with dendrite-like structures for context-dependent processing of information. The dendritic segments process an additional context signal encoding task information and subsequently modulate the feedforward activity of the excitatory neuron. Additionally, it provides an efficient mechanism for controlling the sparsity in activations using k-WTA (k-Winners-Take-All) activations and Heterogeneous dropout mechanism that encourages the model to use a different set of neurons for each task. This provides an effective approach for maintaining a balance between reusability of features and interference which is critical for enabling CL. Furthermore, it complements the error-based learning with the “fire together, wire together” learning paradigm which further strengthen the association between the context signal and dendritic segments which process them and facilitates context-dependent gating. To further mitigate forgetting, it incorporates synaptic consolidation in conjunction with experience replay.
-
公开(公告)号：US20230385644A1
公开(公告)日：2023-11-30
申请号：US17853682
申请日：2022-06-29
Applicant: NavInfo Europe B.V.
Inventor： Arnav Varma , Elahe Arani , Bahram Zonooz
CPC classification number: G06N3/082 , G06N3/0481
Abstract: A computer-implemented method for general continual learning combines rehearsal-based methods with dynamic modularity and compositionality. Concretely, the method aims at achieving three objectives: dynamic, sparse, and compositional response to inputs; competent application performance; and—reducing catastrophic forgetting. The proposed method can work without knowledge of task-identities at test-time, it does not employ task-boundaries and it has bounded memory even when training on longer sequences.
-
公开(公告)号：US20230281985A1
公开(公告)日：2023-09-07
申请号：US17686273
申请日：2022-03-03
Applicant: NavInfo Europe B.V.
Inventor： Naresh Kumar Gurulingan , Elahe Arani , Bahram Zonooz
Abstract: A deep learning framework in multi-task learning for finding a sharing scheme of representations in the decoder to best curb task interference while benefiting from complementary information sharing. A deep-learning based computer-implemented method for multi-task learning, the method including the step of progressively fusing decoders by grouping tasks stage-by-stage based on a pairwise similarity matrix between learned representations of different task decoders.
-
公开(公告)号：US20230281978A1
公开(公告)日：2023-09-07
申请号：US17686267
申请日：2022-03-03
Applicant: NavInfo Europe B.V.
Inventor： Shruthi Gowda , Bahram Zonooz , Elahe Arani
CPC classification number: G06V10/82 , G06T7/13 , G06N3/0454 , G06T2207/20084 , G06T2207/20081
Abstract: A computer implemented method to distill an inductive bias in a deep neural network operating on image data, the deep neural network comprising a standard network that receives original images from the image data, and an inductive-bias network that receives shape data of the images, and a bias alignment is performed on the standard network and inductive-bias network in feature space and decision space to enable the networks to learn both local texture information and global shape information to produce high-level, generic representations.
-
公开(公告)号：US11538166B2
公开(公告)日：2022-12-27
申请号：US17107283
申请日：2020-11-30
Applicant: NavInfo Europe B.V.
Inventor： Elahe Arani , Shabbir Marzban , Andrei Pata , Bahram Zonooz
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.
-
-
-
-
-
-
-
-
-
Search Results
42
records
(took 0.012 seconds)
