公开(公告)号：US20240020844A1

公开(公告)日：2024-01-18

申请号：US18349726

申请日：2023-07-10

申请人： QUALCOMM Incorporated

发明人： Debasmit DAS ,  Shubhankar Mangesh BORSE ,  Hyojin PARK ,  Kambiz AZARIAN YAZDI ,  Hong CAI ,  Risheek GARREPALLI ,  Fatih Murat PORIKLI

IPC分类号： G06T7/11

CPC分类号： G06T7/11 ,  G06T2207/20081 ,  G06T2207/20004

摘要： Systems and techniques are provided for processing data (e.g., image data). For instance, according to some aspects of the disclosure, a method may include receiving, at a transformer of a machine learning system, learnable queries, keys, and values obtained from a feature map of a segmentation model of the machine learning system. The method may further include learning, via the transformer, a mapping between an unsupervised output and a supervised output of the segmentation model based on the feature map.

公开(公告)号：US20240095504A1

公开(公告)日：2024-03-21

申请号：US17932941

申请日：2022-09-16

申请人： QUALCOMM Incorporated

发明人： Debasmit DAS ,  Jamie Menjay LIN

IPC分类号： G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06N5/04

CPC分类号： G06N3/0481 ,  G06N3/063 ,  G06N3/08 ,  G06N5/04

摘要： Certain aspects of the present disclosure provide techniques and apparatus for feature masking. A feature tensor is accessed in a neural network, and a feature mask is generated by processing the feature tensor using a masking subnetwork, where the masking subnetwork was trained based at least in part on a polarization constraint and an activation constraint to generate feature masks. A masked feature tensor is generated based on the feature tensor and the feature mask, and an output inference is generated using the neural network based at least in part on the masked feature tensor.

公开(公告)号：US20230252658A1

公开(公告)日：2023-08-10

申请号：US17650027

申请日：2022-02-04

申请人： QUALCOMM Incorporated

发明人： Hong CAI ,  Shichong PENG ,  Janarbek MATAI ,  Jamie Menjay LIN ,  Debasmit DAS ,  Fatih Murat PORIKLI

IPC分类号： G06T7/50 ,  G06T7/10 ,  G06N3/04

CPC分类号： G06T7/50 ,  G06T7/10 ,  G06N3/0454 ,  G06T2207/20084 ,  G06T2207/20212

摘要： Certain aspects of the present disclosure provide techniques for generating fine depth maps for images of a scene based on semantic segmentation and segment-based refinement neural networks. An example method generally includes generating, through a segmentation neural network, a segmentation map based on an image of a scene. The segmentation map generally comprises a map segmenting the scene into a plurality of regions, and each region of the plurality of regions is generally associated with one of a plurality of categories. A first depth map of the scene is generated through a first depth neural network based on a depth measurement of the scene. A second depth map of the scene is generated through a depth refinement neural network based on the segmentation map and the first depth map. One or more actions are taken based on the second depth map of the scene.

公开(公告)号：US20230154005A1

公开(公告)日：2023-05-18

申请号：US17807614

申请日：2022-06-17

申请人： QUALCOMM Incorporated

发明人： Shubhankar Mangesh BORSE ,  Hyojin PARK ,  Hong CAI ,  Debasmit DAS ,  Risheek GARREPALLI ,  Fatih Murat PORIKLI

IPC分类号： G06T7/10 ,  G06N3/08

CPC分类号： G06T7/10 ,  G06N3/08 ,  G06T2207/20084 ,  G06T2207/20081

摘要： Aspects of the present disclosure relate to a novel framework for integrating both semantic and instance contexts for panoptic segmentation. In one example aspect, a method for processing image data includes: processing semantic feature data and instance feature data with a panoptic encoding generator to generate a panoptic encoding; processing the panoptic encoding to generate a panoptic segmentation features; and generating the panoptic segmentation mask based on the panoptic segmentation features.

公开(公告)号：US20240303497A1

公开(公告)日：2024-09-12

申请号：US18360712

申请日：2023-07-27

申请人： QUALCOMM Incorporated

发明人： Jungsoo LEE ,  Debasmit DAS ,  Sungha CHOI

IPC分类号： G06N3/091 ,  G06N3/045

CPC分类号： G06N3/091 ,  G06N3/045

摘要： A processor-implemented method for adapting an artificial neural network (ANN) at test-time includes receiving by a first ANN model and a second ANN model, a test data set. The test data set includes unlabeled data samples. The first ANN model is pretrained using a training data set and the test data set. The first ANN model generates first estimated labels for the test data set. The second ANN model generates second estimated labels for the test data set. Samples of the test data set are selected based on a confidence difference between the first estimated labels and the second estimated labels. The second ANN model is retrained based on the selected samples.

公开(公告)号：US20240273742A1

公开(公告)日：2024-08-15

申请号：US18165163

申请日：2023-02-06

申请人： QUALCOMM Incorporated

发明人： Debasmit DAS ,  Varun RAVI KUMAR ,  Shubhankar Mangesh BORSE ,  Senthil Kumar YOGAMANI

IPC分类号： G06T7/50 ,  G06T7/10 ,  G06V10/26 ,  G06V10/70 ,  G06V10/764 ,  G06V10/82

CPC分类号： G06T7/50 ,  G06T7/10 ,  G06V10/26 ,  G06V10/764 ,  G06V10/768 ,  G06V10/82 ,  G06T2207/20021 ,  G06T2207/20072 ,  G06T2207/20081 ,  G06T2207/20084

摘要： Disclosed are systems, apparatuses, processes, and computer-readable media for processing image data. For example, a process can include obtaining segmentation information associated with an image of a scene, the image including a plurality of pixels having a resolution, and obtaining depth information associated with one or more objects in the scene. A plurality of features can be generated corresponding to the plurality of pixels, wherein each feature of the plurality of features corresponds to a particular pixel of the plurality of pixels, and wherein each feature includes respective segmentation information of the particular pixel and respective depth information of the particular pixel. The plurality of features can be processed to generate a dense depth output corresponding to the image.

公开(公告)号：US20240161368A1

公开(公告)日：2024-05-16

申请号：US18460903

申请日：2023-09-05

申请人： QUALCOMM Incorporated

发明人： Shubhankar Mangesh BORSE ,  Debasmit DAS ,  Hyojin PARK ,  Hong CAI ,  Risheek GARREPALLI ,  Fatih Murat PORIKLI

IPC分类号： G06T11/60 ,  G06T3/40 ,  G06T7/12 ,  G06T7/50 ,  G06V10/44

CPC分类号： G06T11/60 ,  G06T3/40 ,  G06T7/12 ,  G06T7/50 ,  G06V10/44

摘要： Certain aspects of the present disclosure provide techniques and apparatus for regenerative learning to enhance dense predictions. In one example method, an input image is accessed. A dense prediction output is generated based on the input image using a dense prediction machine learning (ML) model, and a regenerated version of the input image is generated. A first loss is generated based on the input image and a corresponding ground truth dense prediction, and a second loss is generated based on the regenerated version of the input image. One or more parameters of the dense prediction ML model are updated based on the first and second losses.

公开(公告)号：US20220230066A1

公开(公告)日：2022-07-21

申请号：US17648415

申请日：2022-01-19

申请人： QUALCOMM Incorporated

发明人： Debasmit DAS ,  Fatih Murat PORIKLI ,  Sungrack YUN

IPC分类号： G06N3/08 ,  G06F7/76 ,  G06N3/04

摘要： Techniques for cross-domain adaptive learning are provided. A target domain feature extraction model is tuned from a source domain feature extraction model trained on a source data set, where the tuning is performed using a mask generation model trained on a target data set, and the tuning is performed using the target data set.

公开(公告)号：US20240078800A1

公开(公告)日：2024-03-07

申请号：US17939361

申请日：2022-09-07

申请人： QUALCOMM Incorporated

发明人： Saeed VAHIDIAN ,  Manoj BHAT ,  Debasmit DAS ,  Shizhong Steve HAN ,  Fatih Murat PORIKLI

IPC分类号： G06V10/82 ,  G06N3/08 ,  G06V10/764 ,  G06V10/774

CPC分类号： G06V10/82 ,  G06N3/08 ,  G06V10/764 ,  G06V10/774

摘要： A method receives first and second data generated from a first and second domains including first and second set of objects, receiving first class labels for each of the first set of objects, and receiving second class labels for each of the second set of objects. The method generates a training dataset by augmenting the first data and corresponding first class labels, and locally updating neural network parameters of a model based on the training dataset. The method generates a validation dataset by augmenting the second data and corresponding second class labels, and globally updating the neural network parameters of the model based on the validation dataset. The method also generates multiple target labels for target data generated from a target domain including a third set of objects after globally updating the neural network parameters of the model based on the validation dataset.

公开(公告)号：US20240078797A1

公开(公告)日：2024-03-07

申请号：US18364728

申请日：2023-08-03

申请人： QUALCOMM Incorporated

发明人： Kambiz AZARIAN YAZDI ,  Debasmit DAS ,  Hyojin PARK ,  Fatih Murat PORIKLI

IPC分类号： G06V10/778 ,  G06N3/0895 ,  G06V10/26 ,  G06V10/82

CPC分类号： G06V10/778 ,  G06N3/0895 ,  G06V10/267 ,  G06V10/82

摘要： Techniques and systems are provided for performing online adaptation of machine learning model(s). For example, a process may include obtaining features extracted from a image by a machine learning model during inference and determining, by the machine learning model based on the features during inference, a plurality of keypoint estimates in the image and/or a bounding region estimate associated with an object in the image. The process may further include generating pseudo-label(s) based on the plurality of keypoint estimates and/or the bounding region estimate. The process may include determining at least one self-supervised loss based on the plurality of keypoint estimates and/or the bounding region estimate. The process may further include adapting, based on the at least one self-supervised loss, parameter(s) of the machine learning model. The process may include generating, using the machine learning model with the adapted parameter(s), a segmentation mask for the image (or another image).