-
公开(公告)号：WO2023086192A1
公开(公告)日：2023-05-19
申请号：PCT/US2022/047232
申请日：2022-10-20
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： ZHUANG, Bingbing , SCHULTER, Samuel , TSAI, Yi-Hsuan , LIU, Buyu , LI, Nanbo
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：WO2022103753A1
公开(公告)日：2022-05-19
申请号：PCT/US2021/058622
申请日：2021-11-09
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： TSAI, Yi-Hsuan , YU, Xiang , ZHUANG, Bingbing , CHANDRAKER, Manmohan , KIM, Donghyun
Abstract: Video methods and systems include extracting (204/206) 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 (218) 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：WO2020097182A1
公开(公告)日：2020-05-14
申请号：PCT/US2019/060037
申请日：2019-11-06
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： SOHN, Kihyuk , CHANDRAKER, Manmohan , TSAI, Yi-Hsuan
Abstract: A method for protecting visual private data by preventing data reconstruction from latent representations of deep networks is presented. The method includes obtaining latent features (316) from an input image (312) and learning, via an adversarial reconstruction learning framework (318), privacy -preserving feature representations to maintain utility performance and prevent the data reconstruction by: simulating a black-box model inversion attack by training a decoder (332) to reconstruct the input image from the latent features and training an encoder (314) to maximize a reconstruction error to prevent the decoder from inverting the latent features while minimizing the task loss.
-
公开(公告)号：WO2022103684A1
公开(公告)日：2022-05-19
申请号：PCT/US2021/058407
申请日：2021-11-08
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： SUH, Yumin , YU, Xiang , TSAI, Yi-Hsuan , FARAKI, Masoud , CHANDRAKER, Manmohan
IPC: G06K9/00
Abstract: A method for employing facial information in unsupervised person re-identification is presented. The method includes extracting (1001), by a body feature extractor, body features from a first data stream, extracting (1003), by a head feature extractor, head features from a second data stream, outputting (1005) a body descriptor vector from the body feature extractor, outputting (1007) a head descriptor vector from the head feature extractor, and concatenating (1009) the body descriptor vector and the head descriptor vector to enable a model to generate a descriptor vector.
-
公开(公告)号：WO2022072776A1
公开(公告)日：2022-04-07
申请号：PCT/US2021/053086
申请日：2021-10-01
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： YU, Xiang , TSAI, Yi-Hsuan , PITTALUGA, Francesco , FARAKI, Masoud , CHANDRAKER, Manmohan , ZHU, Yuqing
Abstract: A method for employing a general label space voting-based differentially private federated learning (DPFL) framework is presented. The method includes labeling (1010) 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 (1020) 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 (1030) 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.
-
Patent Agency Ranking
公开(公告)号：WO2021243029A1
公开(公告)日：2021-12-02
申请号：PCT/US2021/034528
申请日：2021-05-27
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： CHANDRAKER, Manmohan , WANG, Ting , XU, Xiang , PITTALUGA, Francesco , SHARMA, Gaurav , TSAI, Yi-Hsuan , FARAKI, Masoud , CHEN, Yuheng , TIAN, Yue , HUANG, Ming-Fang , FANG, Jian
Abstract: Methods and systems for training a neural network include generating (801) an image of a mask. A copy of an image is generated (302) from an original set of training data. The copy is altered (302) to add the image of a mask to a face detected within the copy. An augmented set of training data is generated (302) that includes the original set of training data and the altered copy. A neural network model is trained (304) to recognize masked faces using the augmented set of training data.
-
公开(公告)号：WO2023086196A1
公开(公告)日：2023-05-19
申请号：PCT/US2022/047514
申请日：2022-10-24
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： FARAKI, Masoud , TSAI, Yi-Hsuan , YU, Xiang , SCHULTER, Samuel , SUH, Yumin , SIMON, Christian
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：WO2022103748A1
公开(公告)日：2022-05-19
申请号：PCT/US2021/058612
申请日：2021-11-09
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： YU, Xiang , TSAI, Yi-Hsuan , FARAKI, Masoud , MOSLEMI, Ramin , CHANDRAKER, Manmohan , LIU, Chang
Abstract: A method for training a model for face recognition is provided. The method forward trains (610) a training batch of samples to form a face recognition model w(t), and calculates (620) sample weights for the batch. The method obtains (630) 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 (640) a validation batch of samples to the face recognition model what(t). The method obtains (650) 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 (660) a training batch upgraded gradient based on the updated sample-level importance weight of the training batch samples, and updates (660), using the upgraded gradient, the model w(t) to a trained model w(t+l) corresponding to a next iteration.
-
公开(公告)号：WO2022103682A1
公开(公告)日：2022-05-19
申请号：PCT/US2021/058404
申请日：2021-11-08
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： FARAKI, Masoud , YU, Xiang , TSAI, Yi-Hsuan , SUH, Yumin , CHANDRAKER, Manmohan
Abstract: A method for improving face recognition from unseen domains including obtaining (1001) face images with associated identities from a plurality of datasets, randomly (1003) selecting two datasets of the plurality of datasets to train a model, sampling (1005) batch face images and their corresponding labels, sampling (1007) 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 (1009) a forward pass by using the samples of the selected two datasets, finding (1011) representations of the face images by using a backbone convolutional neural network (CNN), generating (1013) 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 (1015) the covariances to compute a cross-domain similarity loss function.
-
公开(公告)号：WO2021097055A1
公开(公告)日：2021-05-20
申请号：PCT/US2020/060178
申请日：2020-11-12
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： TSAI, Yi-Hsuan , SCHULTER, Samuel , CHANDRAKER, Manmohan , PAUL, Sujoy
Abstract: Systems and methods for adapting semantic segmentation across domains is provided. The method includes inputting (720) a source image into a segmentation network, and inputting (710) a target image into the segmentation network. The method further includes identifying (760) category wise features for the source image and the target image using category wise pooling, and discriminating (780) between the category wise features for the source image and the target image. The method further includes training (730) 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.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.031 seconds)
