公开(公告)号：US20240078679A1

公开(公告)日：2024-03-07

申请号：US17901429

申请日：2022-09-01

Applicant: QUALCOMM Incorporated

Inventor： Chung-Chi TSAI ,  Shubhankar Mangesh BORSE ,  Meng-Lin WU ,  Venkata Ravi Kiran DAYANA ,  Fatih Murat PORIKLI ,  An CHEN

IPC: G06T7/11 ,  G06T7/73

CPC classification number: G06T7/11 ,  G06T7/74 ,  G06T2207/20112

Abstract: Methods, systems, and apparatuses for image segmentation are provided. For example, a computing device may obtain an image, and may apply a process to the image to generate input image feature data and input image segmentation data. Further, the computing device may obtain reference image feature data and reference image classification data for a plurality of reference images. The computing device may generate reference image segmentation data based on the reference image feature data, the reference image classification data, and the input image feature data. The computing device may further blend the input image segmentation data and the reference image segmentation data to generate blended image segmentation data. The computing device may store the blended image segmentation data within a data repository. In some examples, the computing device provides the blended image segmentation data for display.

公开(公告)号：US20220156528A1

公开(公告)日：2022-05-19

申请号：US17528141

申请日：2021-11-16

Applicant: QUALCOMM Incorporated

Inventor： Shubhankar Mangesh BORSE ,  Fatih Murat PORIKLI ,  Yizhe ZHANG ,  Ying WANG

IPC: G06K9/62 ,  G06N3/08

Abstract: A method applies a distance-based loss function to a boundary recognition model. The method classifies boundaries of an input with the boundary recognition model. The method also performs semantic segmentation based on the classifying of the boundaries, and outputting a segmentation map showing different classes of objects from the input, based on the semantic segmentation. The method may train an inverse transforming artificial neural network to predict a perspective transformation of an image so that the trained artificial neural network represents the distance-based loss function. The method may freeze weights of the inverse transforming artificial neural network, after training, to obtain the distance-based loss function. Training of the inverse transforming artificial neural network may include generating shifted, translated, and scaled versions of the image such that a ground truth comprises values corresponding to the amounts of shifting, translating, and scaling.

公开(公告)号：US20250131606A1

公开(公告)日：2025-04-24

申请号：US18492572

申请日：2023-10-23

Applicant: QUALCOMM Incorporated

Inventor： Shubhankar Mangesh BORSE ,  Risheek GARREPALLI ,  Qiqi HOU ,  Jisoo JEONG ,  Shreya KADAMBI ,  Munawar HAYAT ,  Fatih Murat PORIKLI

IPC: G06T11/00 ,  G06T3/40

Abstract: A processor-implemented method includes receiving a text-semantic input at a first stage of a neural network, including a first convolutional block and no attention layers. The method receives, at a second stage, a first output from the first stage. The second stage comprises a first down sampling block including a first attention layer and a second convolutional block. The method receives, at a third stage, a second output from the second stage. The third stage comprises a first up sampling block including a second attention layer and a first set of convolutional blocks. The method receives, at a fourth stage, the first output from the first stage and a third output from the third stage. The fourth stage comprises a second up sampling block including no attention layers and a second set of convolutional blocks. The method generates an image at the fourth stage, based on the text-semantic input.

公开(公告)号：US20250131325A1

公开(公告)日：2025-04-24

申请号：US18492492

申请日：2023-10-23

Applicant: QUALCOMM Incorporated

Inventor： Risheek GARREPALLI ,  Shubhankar Mangesh BORSE ,  Jisoo JEONG ,  Qiqi HOU ,  Shreya KADAMBI ,  Munawar HAYAT ,  Fatih Murat PORIKLI

IPC: G06N20/00

Abstract: A method for training a diffusion model includes compressing the diffusion model by removing at least one of: one or more model parameters or one or more giga multiply-accumulate operations (GMACs). The method also includes performing guidance conditioning to train the compressed diffusion model, the guidance conditioning combining a conditional output and an unconditional output from respective teacher models. The method further includes performing, after the guidance conditioning, step distillation on the compressed diffusion model.

公开(公告)号：US20250131277A1

公开(公告)日：2025-04-24

申请号：US18492529

申请日：2023-10-23

Applicant: QUALCOMM Incorporated

Inventor： Risheek GARREPALLI ,  Shubhankar Mangesh BORSE ,  Jisoo JEONG ,  Qiqi HOU ,  Shreya KADAMBI ,  Munawar HAYAT ,  Fatih Murat PORIKLI

IPC: G06N3/09

Abstract: A method for training a control neural network includes initializing a baseline diffusion model for training the control neural network, each stage of a control neural network training pipeline corresponding to an element of the baseline diffusion model. The method also includes training, the control neural network, in a stage-wise manner, each stage of the control neural network training pipeline receiving an input from a previous stage of the control neural network training pipeline and the corresponding element of the diffusion model.

公开(公告)号：US20250131276A1

公开(公告)日：2025-04-24

申请号：US18492508

申请日：2023-10-23

Applicant: QUALCOMM Incorporated

Inventor： Risheek GARREPALLI ,  Shubhankar Mangesh BORSE ,  Jisoo JEONG ,  Qiqi HOU ,  Shreya KADAMBI ,  Munawar HAYAT ,  Fatih Murat PORIKLI

IPC: G06N3/09

Abstract: A method for training a diffusion model includes randomly selecting, for each iteration of a step distillation training process, a teacher model of a group of teacher models. The method also includes applying, at each iteration, a clipped input space within step distillation of the randomly selected teacher model. The method further includes updating, at each iteration, parameters of the diffusion model based on guidance from the randomly selected teacher model.

公开(公告)号：US20240412493A1

公开(公告)日：2024-12-12

申请号：US18537404

申请日：2023-12-12

Applicant: QUALCOMM Incorporated

Inventor： Risheek GARREPALLI ,  Yunxiao SHI ,  Hong CAI ,  Yinhao ZHU ,  Shubhankar Mangesh BORSE ,  Jisoo JEONG ,  Debasmit DAS ,  Manish Kumar SINGH ,  Rajeev YASARLA ,  Shizhong Steve HAN ,  Fatih Murat PORIKLI

IPC: G06V10/776 ,  G06T7/50 ,  G06V10/764 ,  G06V10/82 ,  G06V20/70

Abstract: Systems and techniques are provided for processing image data. According to some aspects, a computing device can generate a gradient (e.g., a classifier gradient using a trained classifier) associated with a current sample. The computing device can combine the gradient with an iterative model estimated score function or data associated with the current sample to generate a score function estimate. The computing device can predict, using the diffusion machine learning model and based on the score function estimate, a new sample.

公开(公告)号：US20240020844A1

公开(公告)日：2024-01-18

申请号：US18349726

申请日：2023-07-10

Applicant: QUALCOMM Incorporated

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

IPC: G06T7/11

CPC classification number: G06T7/11 ,  G06T2207/20081 ,  G06T2207/20004

Abstract: 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.