公开(公告)号：US20240029822A1

公开(公告)日：2024-01-25

申请号：US18479416

申请日：2023-10-02

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Hans Peter Graf ,  Ligong Han

IPC: G16B15/30 ,  G06N3/08 ,  G16B40/20 ,  G06N3/045

CPC classification number: G16B15/30 ,  G06N3/08 ,  G16B40/20 ,  G06N3/045

Abstract: A computer-implemented method is provided for generating new binding peptides to Major Histocompatibility Complex (MHC) proteins. The method includes training, by a processor device, a Generative Adversarial Network GAN having a generator and a discriminator only on a set of binding peptide sequences given training data comprising the set of binding peptide sequences and a set of non-binding peptide sequences. A GAN training objective includes the discriminator being iteratively updated to distinguish generated peptide sequences from sampled binding peptide sequences as fake or real and the generator being iteratively updated to fool the discriminator. The training includes optimizing the GAN training objective while learning two projection vectors for a binding class with two cross-entropy losses. A first loss discriminating binding peptide sequences in the training data from non-binding peptide sequences in the training data. A second loss discriminating generated binding peptide sequences from non-binding peptide sequences in the training data.

公开(公告)号：US20240029821A1

公开(公告)日：2024-01-25

申请号：US18479409

申请日：2023-10-02

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Hans Peter Graf ,  Ligong Han

IPC: G16B15/30 ,  G06N3/08 ,  G16B40/20 ,  G06N3/045

CPC classification number: G16B15/30 ,  G06N3/08 ,  G16B40/20 ,  G06N3/045

Abstract: A computer-implemented method is provided for generating new binding peptides to Major Histocompatibility Complex (MHC) proteins. The method includes training, by a processor device, a Generative Adversarial Network GAN having a generator and a discriminator only on a set of binding peptide sequences given training data comprising the set of binding peptide sequences and a set of non-binding peptide sequences. A GAN training objective includes the discriminator being iteratively updated to distinguish generated peptide sequences from sampled binding peptide sequences as fake or real and the generator being iteratively updated to fool the discriminator. The training includes optimizing the GAN training objective while learning two projection vectors for a binding class with two cross-entropy losses. A first loss discriminating binding peptide sequences in the training data from non-binding peptide sequences in the training data. A second loss discriminating generated binding peptide sequences from non-binding peptide sequences in the training data.

公开(公告)号：US20230154167A1

公开(公告)日：2023-05-18

申请号：US17966017

申请日：2022-10-14

Applicant: NEC Laboratories America, Inc.

Inventor： Kai Li ,  Renqiang Min ,  Hans Peter Graf

IPC: G06V10/774 ,  G06V10/25 ,  G06V10/764

CPC classification number: G06V10/7747 ,  G06V10/25 ,  G06V10/765 ,  G06V2201/07

Abstract: A method for implementing source-free domain adaptive detection is presented. The method includes, in a pretraining phase, applying strong data augmentation to labeled source images to produce perturbed labeled source images and training an object detection model by using the perturbed labeled source images to generate a source-only model. The method further includes, in an adaptation phase, training a self-trained mean teacher model by generating a weakly augmented image and multiple strongly augmented images from unlabeled target images, generating a plurality of region proposals from the weakly augmented image, selecting a region proposal from the plurality of region proposals as a pseudo ground truth, detecting, by the self-trained mean teacher model, object boxes and selecting pseudo ground truth boxes by employing a confidence constraint and a consistency constraint, and training a student model by using one of the multiple strongly augmented images jointly with an object detection loss.

公开(公告)号：US20230153606A1

公开(公告)日：2023-05-18

申请号：US17968923

申请日：2022-10-19

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Kai Li ,  Hans Peter Graf ,  Zhiheng Li

IPC: G06N3/08 ,  G06N3/04 ,  G06F40/30 ,  G06V10/774 ,  G06V10/82 ,  G06F40/279

CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06F40/30 ,  G06V10/774 ,  G06V10/82 ,  G06F40/279

Abstract: A method is provided that includes training a CLIP model to learn embeddings of images and text from matched image-text pairs. The text represents image attributes. The method trains a StyleGAN on images in a training dataset of matched image-text pairs. The method also trains, using a CLIP model guided contrastive loss which attracts matched text embedding pairs and repels unmatched pairs, a text-to-direction model to predict a text direction that is semantically aligned with an input text responsive to the input text and a random latent code. A triplet loss is used to learn text directions using the embeddings learned by the trained CLIP model. The method generates, by the trained StyleGAN, positive and negative synthesized images by respectively adding and subtracting the text direction in the latent space of the trained StyleGAN corresponding to a word for each of the words in the training dataset.

公开(公告)号：US20220328127A1

公开(公告)日：2022-10-13

申请号：US17711310

申请日：2022-04-01

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Hans Peter Graf ,  Ligong Han

IPC: G16B15/30 ,  G16B40/20 ,  G06N3/04 ,  G06N3/08

Abstract: A computer-implemented method is provided for generating new binding peptides to Major Histocompatibility Complex (MHC) proteins. The method includes training, by a processor device, a Generative Adversarial Network GAN having a generator and a discriminator only on a set of binding peptide sequences given training data comprising the set of binding peptide sequences and a set of non-binding peptide sequences. A GAN training objective includes the discriminator being iteratively updated to distinguish generated peptide sequences from sampled binding peptide sequences as fake or real and the generator being iteratively updated to fool the discriminator. The training includes optimizing the GAN training objective while learning two projection vectors for a binding class with two cross-entropy losses. A first loss discriminating binding peptide sequences in the training data from non-binding peptide sequences in the training data. A second loss discriminating generated binding peptide sequences from non-binding peptide sequences in the training data.

公开(公告)号：US20220319635A1

公开(公告)日：2022-10-06

申请号：US17711617

申请日：2022-04-01

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Hans Peter Graf ,  Ligong Han

IPC: G16B20/30 ,  G06N3/08 ,  G06N3/04 ,  G16B40/20 ,  G16B30/00

Abstract: Methods and systems for training a model include encoding training peptide sequences using an encoder model. A new peptide sequence is generated using a generator model. The encoder model, the generator model, and the discriminator model are trained to cause the generator model to generate new peptides that the discriminator mistakes for the training peptide sequences, including learning projection vectors with respective cross-entropy losses for binding sequences and non-binding sequences.

公开(公告)号：US11423655B2

公开(公告)日：2022-08-23

申请号：US17088043

申请日：2020-11-03

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Yizhe Zhu ,  Asim Kadav ,  Hans Peter Graf

IPC: G06V20/40 ,  G06K9/62

Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing, by a variational autoencoder, a plurality of supervision signals. The method further includes accessing, by the variational autoencoder, a plurality of auxiliary tasks that utilize the supervision signals as reward signals to learn a disentangled representation. The method also includes training the variational autoencoder to disentangle a sequential data input into a time-invariant factor and a time-varying factor using a self-supervised training approach which is based on outputs of the auxiliary tasks obtained by using the supervision signals to accomplish the plurality of auxiliary tasks.

公开(公告)号：US20220101007A1

公开(公告)日：2022-03-31

申请号：US17463757

申请日：2021-09-01

Applicant: NEC Laboratories America, Inc.

Inventor： Asim Kadav ,  Farley Lai ,  Hans Peter Graf ,  Alexandru Niculescu-Mizil ,  Renqiang Min ,  Honglu Zhou

IPC: G06K9/00 ,  G06K9/62 ,  G06T7/73 ,  G06T7/246 ,  G06N3/04

Abstract: A method for using a multi-hop reasoning framework to perform multi-step compositional long-term reasoning is presented. The method includes extracting feature maps and frame-level representations from a video stream by using a convolutional neural network (CNN), performing object representation learning and detection, linking objects through time via tracking to generate object tracks and image feature tracks, feeding the object tracks and the image feature tracks to a multi-hop transformer that hops over frames in the video stream while concurrently attending to one or more of the objects in the video stream until the multi-hop transformer arrives at a correct answer, and employing video representation learning and recognition from the objects and image context to locate a target object within the video stream.

公开(公告)号：US11227108B2

公开(公告)日：2022-01-18

申请号：US16038830

申请日：2018-07-18

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Dinghan Shen ,  Yitong Li

IPC: G06N3/04 ,  G06N5/04 ,  G06F16/35 ,  G06N3/08 ,  G06F40/20 ,  H03M7/30 ,  G06F16/332 ,  G06F16/33 ,  G06F16/335 ,  H04L12/58

Abstract: A computer-implemented method for employing input-conditioned filters to perform natural language processing tasks using a convolutional neural network architecture includes receiving one or more inputs, generating one or more sets of filters conditioned on respective ones of the one or more inputs by implementing one or more encoders to encode the one or more inputs into one or more respective hidden vectors, and implementing one or more decoders to determine the one or more sets of filters based on the one or more hidden vectors, and performing adaptive convolution by applying the one or more sets of filters to respective ones of the one or more inputs to generate one or more representations.

公开(公告)号：US11087184B2

公开(公告)日：2021-08-10

申请号：US16580199

申请日：2019-09-24

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Kai Li ,  Bing Bai ,  Hans Peter Graf

IPC: G06K9/62 ,  G06N3/08 ,  G06K9/46

Abstract: A computer-implemented method and system are provided for training a model for New Class Categorization (NCC) of a test image. The method includes decoupling, by a hardware processor, a feature extraction part from a classifier part of a deep classification model by reparametrizing learnable weight variables of the classifier part as a combination of learnable variables of the feature extraction part and of a classification weight generator of the classifier part. The method further includes training, by the hardware processor, the deep classification model to obtain a trained deep classification model by (i) learning the feature extraction part as a multiclass classification task, and (ii) episodically training the classifier part by learning a classification weight generator which outputs classification weights given a training image.