-
公开(公告)号：US20220108226A1
公开(公告)日：2022-04-07
申请号：US17491663
申请日：2021-10-01
Applicant: NEC Laboratories America, Inc.
Inventor： Xiang Yu , Yi-Hsuan Tsai , Francesco Pittaluga , Masoud Faraki , Manmohan Chandraker , Yuqing Zhu
Abstract: A method for employing a general label space voting-based differentially private federated learning (DPFL) framework is presented. The method includes labeling a first subset of unlabeled data from a first global server, to generate first pseudo-labeled data, by employing a first voting-based DPFL computation where each agent trains a local agent model by using private local data associated with the agent, labeling a second subset of unlabeled data from a second global server, to generate second pseudo-labeled data, by employing a second voting-based DPFL computation where each agent maintains a data-independent feature extractor, and training a global model by using the first and second pseudo-labeled data to provide provable differential privacy (DP) guarantees for both instance-level and agent-level privacy regimes.
-
公开(公告)号：US20210150275A1
公开(公告)日：2021-05-20
申请号：US17094261
申请日：2020-11-10
Applicant: NEC Laboratories America, Inc.
Inventor： Samuel Schulter , Gaurav Sharma , Yi-Hsuan Tsai , Manmohan Chandraker , Xiangyun Zhao
Abstract: Methods and systems for object detection include training dataset-specific object detectors using respective annotated datasets, each of the annotated datasets including annotations for a respective set of one or more object classes. The annotated datasets are cross-annotated using the dataset-specific object detectors. A unified object detector is trained, using the cross-annotated datasets, to detect all of the object classes of the annotated datasets. Objects are detected in an input image using the unified object detector.
-
公开(公告)号：US20210110147A1
公开(公告)日：2021-04-15
申请号：US17128565
申请日：2020-12-21
Applicant: NEC Laboratories America, Inc.
Inventor： Yi-Hsuan Tsai , Kihyuk Sohn , Buyu Liu , Manmohan Chandraker , Jong-Chyi Su
Abstract: Systems and methods for human detection 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 humans in one or more different scenes. 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：US12254681B2
公开(公告)日：2025-03-18
申请号：US17903393
申请日：2022-09-06
Applicant: NEC Laboratories America, Inc.
Inventor： Yi-Hsuan Tsai , Bingbing Zhuang , Samuel Schulter , Buyu Liu , Sparsh Garg , Ramin Moslemi , Inkyu Shin
IPC: G06K9/00 , G01S17/89 , G06V10/776 , G06V10/80
Abstract: Systems and methods are provided for multi-modal test-time adaptation. The method includes inputting a digital image into a pre-trained Camera Intra-modal Pseudo-label Generator, and inputting a point cloud set into a pre-trained Lidar Intra-modal Pseudo-label Generator. The method further includes applying a fast 2-dimension (2D) model, and a slow 2D model, to the inputted digital image to apply pseudo-labels, and applying a fast 3-dimension (3D) model, and a slow 3D model, to the inputted point cloud set to apply pseudo-labels. The method further includes fusing pseudo-label predictions from the fast models and the slow models through an Inter-modal Pseudo-label Refinement module to obtain robust pseudo labels, and measuring a prediction consistency for the pseudo-labels. The method further includes selecting confident pseudo-labels from the robust pseudo labels and measured prediction consistencies to form a final cross-modal pseudo-label set as a self-training signal, and updating batch parameters utilizing the self-training signal.
-
公开(公告)号：US11947626B2
公开(公告)日：2024-04-02
申请号：US17519950
申请日：2021-11-05
Applicant: NEC Laboratories America, Inc.
Inventor： Masoud Faraki , Xiang Yu , Yi-Hsuan Tsai , Yumin Suh , Manmohan Chandraker
IPC: G06F18/214 , G06N3/04 , G06V40/16
CPC classification number: G06F18/214 , G06N3/04 , G06V40/161
Abstract: A method for improving face recognition from unseen domains by learning semantically meaningful representations is presented. The method includes obtaining face images with associated identities from a plurality of datasets, randomly selecting two datasets of the plurality of datasets to train a model, sampling batch face images and their corresponding labels, sampling triplet samples including one anchor face image, a sample face image from a same identity, and a sample face image from a different identity than that of the one anchor face image, performing a forward pass by using the samples of the selected two datasets, finding representations of the face images by using a backbone convolutional neural network (CNN), generating covariances from the representations of the face images and the backbone CNN, the covariances made in different spaces by using positive pairs and negative pairs, and employing the covariances to compute a cross-domain similarity loss function.
-
Patent Agency Ranking
公开(公告)号：US20230153572A1
公开(公告)日：2023-05-18
申请号：US17971204
申请日：2022-10-21
Applicant: NEC Laboratories America, Inc.
Inventor： Masoud Faraki , Yi-Hsuan Tsai , Xiang Yu , Samuel Schulter , Yumin Suh , Christian Simon
Abstract: A computer-implemented method for model training is provided. The method includes receiving, by a hardware processor, sets of images, each set corresponding to a respective task. The method further includes training, by the hardware processor, a task-based neural network classifier having a center and a covariance matrix for each of a plurality of classes in a last layer of the task-based neural network classifier and a plurality of convolutional layers preceding the last layer, by using a similarity between an image feature of a last convolutional layer from among the plurality of convolutional layers and the center and the covariance matrix for a given one of the plurality of classes, the similarity minimizing an impact of a data model forgetting problem.
-
公开(公告)号：US11610420B2
公开(公告)日：2023-03-21
申请号：US17128565
申请日：2020-12-21
Applicant: NEC Laboratories America, Inc.
Inventor： Yi-Hsuan Tsai , Kihyuk Sohn , Buyu Liu , Manmohan Chandraker , Jong-Chyi Su
Abstract: Systems and methods for human detection 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 humans in one or more different scenes. 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：US20220147765A1
公开(公告)日：2022-05-12
申请号：US17519950
申请日：2021-11-05
Applicant: NEC Laboratories America, Inc.
Inventor： Masoud Faraki , Xiang Yu , Yi-Hsuan Tsai , Yumin Suh , Manmohan Chandraker
Abstract: A method for improving face recognition from unseen domains by learning semantically meaningful representations is presented. The method includes obtaining face images with associated identities from a plurality of datasets, randomly selecting two datasets of the plurality of datasets to train a model, sampling batch face images and their corresponding labels, sampling triplet samples including one anchor face image, a sample face image from a same identity, and a sample face image from a different identity than that of the one anchor face image, performing a forward pass by using the samples of the selected two datasets, finding representations of the face images by using a backbone convolutional neural network (CNN), generating covariances from the representations of the face images and the backbone CNN, the covariances made in different spaces by using positive pairs and negative pairs, and employing the covariances to compute a cross-domain similarity loss function.
-
公开(公告)号：US20210150281A1
公开(公告)日：2021-05-20
申请号：US17094139
申请日：2020-11-10
Applicant: NEC Laboratories America, Inc.
Inventor： Yi-Hsuan Tsai , Samuel Schulter , Manmohan Chandraker , Sujoy Paul
Abstract: Systems and methods for adapting semantic segmentation across domains is provided. The method includes inputting a source image into a segmentation network, and inputting a target image into the segmentation network. The method further includes identifying category wise features for the source image and the target image using category wise pooling, and discriminating between the category wise features for the source image and the target image. The method further includes training the segmentation network with a pixel-wise cross-entropy loss on the source image, and a weak image classification loss and an adversarial loss on the target image, and outputting a semantically segmented target image.
-
公开(公告)号：US20210110209A1
公开(公告)日：2021-04-15
申请号：US17128612
申请日：2020-12-21
Applicant: NEC Laboratories America, Inc.
Inventor： Yi-Hsuan Tsai , Kihyuk Sohn , Buyu Liu , Manmohan Chandraker , Jong-Chyi Su
Abstract: Systems and methods for construction zone segmentation 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 construction zones scenes having various objects. 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.
-
-
-
-
-
-
-
-
-
Search Results
42
records
(took 0.02 seconds)
