公开(公告)号：US12045992B2

公开(公告)日：2024-07-23

申请号：US17520207

申请日：2021-11-05

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Masoud Faraki ,  Yumin Suh ,  Sparsh Garg ,  Manmohan Chandraker ,  Dongwan Kim

IPC: G06K9/00 ,  G06F18/214 ,  G06F18/2415 ,  G06F18/2431 ,  G06T7/11

CPC classification number: G06T7/11 ,  G06F18/2148 ,  G06F18/2415 ,  G06F18/2431 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods and systems for training a model include combining data from multiple datasets, the datasets having different respective label spaces. Relationships between labels in the different label spaces are identified. A unified neural network model is trained, using the combined data and the identified relationships to generate a unified model, with a class relational binary cross-entropy loss.

公开(公告)号：US11977602B2

公开(公告)日：2024-05-07

申请号：US17521252

申请日：2021-11-08

Applicant: NEC Laboratories America, Inc.

Inventor： Xiang Yu ,  Yi-Hsuan Tsai ,  Masoud Faraki ,  Ramin Moslemi ,  Manmohan Chandraker ,  Chang Liu

IPC: G06K9/00 ,  G06F18/21 ,  G06F18/214 ,  G06N20/00 ,  G06V40/16

CPC classification number: G06F18/214 ,  G06F18/217 ,  G06N20/00 ,  G06V40/172

Abstract: A method for training a model for face recognition is provided. The method forward trains a training batch of samples to form a face recognition model w(t), and calculates sample weights for the batch. The method obtains a training batch gradient with respect to model weights thereof and updates, using the gradient, the model w(t) to a face recognition model what(t). The method forwards a validation batch of samples to the face recognition model what(t). The method obtains a validation batch gradient, and updates, using the validation batch gradient and what(t), a sample-level importance weight of samples in the training batch to obtain an updated sample-level importance weight. The method obtains a training batch upgraded gradient based on the updated sample-level importance weight of the training batch samples, and updates, using the upgraded gradient, the model w(t) to a trained model w(t+1) corresponding to a next iteration.

公开(公告)号：US20230073055A1

公开(公告)日：2023-03-09

申请号：US17903383

申请日：2022-09-06

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Sparsh Garg ,  Manmohan Chandraker ,  Samuel Shulter ,  Vijay Kumar Baikampady Gopalkrishna

IPC: G06T7/11

Abstract: A computer-implemented method for rut detection is provided. The method includes detecting, by a rut detection system, areas in a road-scene image that include ruts with pixel-wise probability values, wherein a higher value indicates a better chance of being a rut. The method further includes performing at least one of rut repair and vehicle rut avoidance responsive to the pixel-wise probability values. The detecting step includes performing neural network-based, pixel-wise semantic segmentation with context information on the road-scene image to distinguish rut pixels from non-rut pixels on a road depicted in the road-scene image.

公开(公告)号：US20220147767A1

公开(公告)日：2022-05-12

申请号：US17521252

申请日：2021-11-08

Applicant: NEC Laboratories America, Inc.

Inventor： Xiang Yu ,  Yi-Hsuan Tsai ,  Masoud Faraki ,  Ramin Moslemi ,  Manmohan Chandraker ,  Chang Liu

IPC: G06K9/62 ,  G06N20/00 ,  G06K9/00

Abstract: A method for training a model for face recognition is provided. The method forward trains a training batch of samples to form a face recognition model w(t), and calculates sample weights for the batch. The method obtains a training batch gradient with respect to model weights thereof and updates, using the gradient, the model w(t) to a face recognition model what(t). The method forwards a validation batch of samples to the face recognition model what(t). The method obtains a validation batch gradient, and updates, using the validation batch gradient and what(t), a sample-level importance weight of samples in the training batch to obtain an updated sample-level importance weight. The method obtains a training batch upgraded gradient based on the updated sample-level importance weight of the training batch samples, and updates, using the upgraded gradient, the model w(t) to a trained model w(t+1) corresponding to a next iteration.

公开(公告)号：US11087142B2

公开(公告)日：2021-08-10

申请号：US16567236

申请日：2019-09-11

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Manmohan Chandraker ,  Shuyang Dai ,  Kihyuk Sohn

IPC: G06K9/00 ,  G06N3/08 ,  G06K9/62

Abstract: Systems and methods for recognizing fine-grained objects are provided. The system divides unlabeled training data from a target domain into two or more target subdomains using an attribute annotation. The system ranks the target subdomains based on a similarity to the source domain. The system applies multiple domain discriminators between each of the target subdomains and a mixture of the source domain and preceding target domains. The system recognizes, using the multiple domain discriminators for the target domain, fine-grained objects.

公开(公告)号：US20210110210A1

公开(公告)日：2021-04-15

申请号：US17128535

申请日：2020-12-21

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Kihyuk Sohn ,  Buyu Liu ,  Manmohan Chandraker ,  Jong-Chyi Su

IPC: G06K9/62 ,  G06K9/00 ,  G06K9/32 ,  B60W30/095 ,  B60W30/09 ,  B60W10/20 ,  B60W10/18 ,  B60W50/00 ,  G08G1/16 ,  G06N3/08

Abstract: Systems and methods for lane marking and road sign recognition are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having lane markings and road signs. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

公开(公告)号：US12131422B2

公开(公告)日：2024-10-29

申请号：US17963471

申请日：2022-10-11

Applicant: NEC Laboratories America, Inc.

Inventor： Bingbing Zhuang ,  Samuel Schulter ,  Yi-Hsuan Tsai ,  Buyu Liu ,  Nanbo Li

IPC: G06T17/00 ,  G06T15/00 ,  G06T15/20 ,  G06V10/774 ,  G06V10/82 ,  G06V20/40

CPC classification number: G06T15/20 ,  G06T15/00 ,  G06T17/00 ,  G06V10/774 ,  G06V10/82 ,  G06V20/41 ,  G06T2200/08 ,  G06T2210/56

Abstract: A method for achieving high-fidelity novel view synthesis and 3D reconstruction for large-scale scenes is presented. The method includes obtaining images from a video stream received from a plurality of video image capturing devices, grouping the images into different image clusters representing a large-scale 3D scene, training a neural radiance field (NeRF) and an uncertainty multilayer perceptron (MLP) for each of the image clusters to generate a plurality of NeRFs and a plurality of uncertainty MLPs for the large-scale 3D scene, applying a rendering loss and an entropy loss to the plurality of NeRFs, performing uncertainty-based fusion to the plurality of NeRFs to define a fused NeRF, and jointly fine-tuning the plurality of NeRFs and the plurality of uncertainty MLPs, and during inference, applying the fused NeRF for novel view synthesis of the large-scale 3D scene.

公开(公告)号：US20240037187A1

公开(公告)日：2024-02-01

申请号：US18484832

申请日：2023-10-11

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Xiang Yu ,  Bingbing Zhuang ,  Manmohan Chandraker ,  Donghyun Kim

IPC: G06F18/213 ,  G06N3/08 ,  G06V10/75 ,  G06F18/22 ,  G06F18/214

CPC classification number: G06F18/213 ,  G06N3/08 ,  G06V10/751 ,  G06F18/22 ,  G06F18/2155

Abstract: Video methods and systems include extracting features of a first modality and a second modality from a labeled first training dataset in a first domain and an unlabeled second training dataset in a second domain. A video analysis model is trained using contrastive learning on the extracted features, including optimization of a loss function that includes a cross-domain regularization part and a cross-modality regularization part.

公开(公告)号：US20240037186A1

公开(公告)日：2024-02-01

申请号：US18484826

申请日：2023-10-11

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Xiang Yu ,  Bingbing Zhuang ,  Manmohan Chandraker ,  Donghyun Kim

IPC: G06F18/213 ,  G06N3/08 ,  G06V10/75 ,  G06F18/22 ,  G06F18/214

CPC classification number: G06F18/213 ,  G06N3/08 ,  G06V10/751 ,  G06F18/22 ,  G06F18/2155

Abstract: Video methods and systems include extracting features of a first modality and a second modality from a labeled first training dataset in a first domain and an unlabeled second training dataset in a second domain. A video analysis model is trained using contrastive learning on the extracted features, including optimization of a loss function that includes a cross-domain regularization part and a cross-modality regularization part.

公开(公告)号：US20220148189A1

公开(公告)日：2022-05-12

申请号：US17520207

申请日：2021-11-05

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Masoud Faraki ,  Yumin Suh ,  Sparsh Garg ,  Manmohan Chandraker ,  Dongwan Kim

IPC: G06T7/11 ,  G06K9/62

Abstract: Methods and systems for training a model include combining data from multiple datasets, the datasets having different respective label spaces. Relationships between labels in the different label spaces are identified. A unified neural network model is trained, using the combined data and the identified relationships to generate a unified model, with a class relational binary cross-entropy loss.