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：US20250124551A1

公开(公告)日：2025-04-17

申请号：US18488786

申请日：2023-10-17

Applicant: QUALCOMM Incorporated

Inventor： Amirhossein HABIBIAN ,  Risheek GARREPALLI ,  Fatih Murat PORIKLI

IPC: G06T5/00

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. During a first iteration of processing data using a first denoising backbone of a teacher diffusion machine learning model, a first latent tensor is generated using a lower resolution block of the first denoising backbone. During a first iteration of processing data using a second denoising backbone of a student diffusion machine learning model, a second latent tensor is generated using an adapter block of the second denoising backbone. A loss is generated based on the first and second latent tensors, and one or more parameters of the adapter block are updated based on the loss.

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：US20240404093A1

公开(公告)日：2024-12-05

申请号：US18327380

申请日：2023-06-01

Applicant: QUALCOMM Incorporated

Inventor： Jisoo JEONG ,  Hong CAI ,  Risheek GARREPALLI ,  Fatih Murat PORIKLI ,  Mathew SAM ,  Khalid TAHBOUB ,  Bing HAN

IPC: G06T7/593

Abstract: Systems and techniques are provided for generating disparity information from two or more images. For example, a process can include obtaining first disparity information corresponding to a pair of images, the pair of images including a first image of a scene and a second image of the scene. The process can include obtaining confidence information associated with the first disparity information. The process can include processing, using a machine learning network, the first disparity information and the confidence information to generate second disparity information corresponding to the pair of images. The process can include combining, based on the confidence information, the first disparity information with the second disparity information to generate a refined disparity map corresponding to the pair of images.

公开(公告)号：US20240161312A1

公开(公告)日：2024-05-16

申请号：US18477493

申请日：2023-09-28

Applicant: QUALCOMM Incorporated

Inventor： Jisoo JEONG ,  Risheek GARREPALLI ,  Hong CAI ,  Fatih Murat PORIKLI

IPC: G06T7/246

CPC classification number: G06T7/248 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A computer-implemented method includes generating a first augmented frame by combining a first image and a first frame of a first frame pair. The computer-implemented method also includes generating, via an optical flow estimation model, a first flow estimation based on a second frame of the first frame pair and the first augmented frame. The computer-implemented method further includes updating one or both of parameters or weights of the optical flow estimation model based on a first loss between the first flow estimation and a training target.

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.