公开(公告)号：US20240095493A1

公开(公告)日：2024-03-21

申请号：US17932527

申请日：2022-09-15

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Jian SHEN

IPC: G06N3/04 ,  G06F7/50 ,  G06F7/523

CPC classification number: G06N3/04 ,  G06F7/50 ,  G06F7/523

Abstract: Certain aspects of the present disclosure provide techniques for desparsified convolution. A weight tensor having unstructured sparsity is accessed, and a densified weight tensor is generated based on the weight tensor by directionally squeezing the weight tensor to remove sparse values, and generating a sparsity map based on the directional squeezing. The densified weight tensor and sparsity map are output for use in a convolutional neural network.

公开(公告)号：US20230259773A1

公开(公告)日：2023-08-17

申请号：US17651549

申请日：2022-02-17

Applicant: QUALCOMM Incorporated

Inventor： Yash Sanjay BHALGAT ,  Fatih Murat PORIKLI ,  Jamie Menjay LIN

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/082 ,  G06N3/04

Abstract: Certain aspects of the present disclosure provide techniques for efficient bottleneck processing via dimensionality transformation. The techniques include receiving a tensor, and processing the tensor in a bottleneck block in a neural network model, comprising applying a space-to-depth tensor transformation, applying a depthwise convolution, and applying a depth-to-space tensor transformation.

公开(公告)号：US20230252658A1

公开(公告)日：2023-08-10

申请号：US17650027

申请日：2022-02-04

Applicant: QUALCOMM Incorporated

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

IPC: G06T7/50 ,  G06T7/10 ,  G06N3/04

CPC classification number: G06T7/50 ,  G06T7/10 ,  G06N3/0454 ,  G06T2207/20084 ,  G06T2207/20212

Abstract: 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：US20230222673A1

公开(公告)日：2023-07-13

申请号：US18180730

申请日：2023-03-08

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Fatih Murat PORIKLI

IPC: G06T7/246 ,  G06T7/73

CPC classification number: G06T7/248 ,  G06F18/24 ,  G06T7/74 ,  G06T2207/10016

Abstract: Systems and techniques are described herein for performing optical flow estimation for one or more frames. For example, a process can include determining an optical flow prediction associated with a plurality of frames. The process can include determining a position of at least one feature associated with a first frame and determining, based on the position of the at least one feature in the first frame and the optical flow prediction, a position estimate of a search area for searching for the at least one feature in a second frame. The process can include determining, from within the search area, a position of the at least one feature in the second frame

公开(公告)号：US20230086378A1

公开(公告)日：2023-03-23

申请号：US17482176

申请日：2021-09-22

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Yash Sanjay BHALGAT ,  Fatih Murat PORIKLI

IPC: G06N3/08 ,  G06N20/10

Abstract: Certain aspects of the present disclosure provide techniques for using shaped convolution kernels, comprising: receiving an input data patch, and processing the input data patch with a shaped kernel to generate convolution output.

公开(公告)号：US20230057454A1

公开(公告)日：2023-02-23

申请号：US17407085

申请日：2021-08-19

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Fatih Murat PORIKLI ,  Mustafa KESKIN

IPC: G06N3/08 ,  G06N3/04

Abstract: Certain aspects of the present disclosure provide techniques for parameterized activation functions. Input data is processed with at least one layer of the neural network model comprising a parameterized activation function, and at least one trainable parameter of the parameterized activation function is updated based at least in part on output from the at least one layer of the neural network model. The at least one trainable parameter may adjust at least one of a range over which the parameterized activation function is nonlinear or a shape of the parameterized activation function, and/or may adjust a location of at least one pivot of the parameterized activation function.

公开(公告)号：US20220398747A1

公开(公告)日：2022-12-15

申请号：US17344283

申请日：2021-06-10

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Fatih Murat PORIKLI

IPC: G06T7/246 ,  G06T7/73 ,  G06K9/62

Abstract: Systems and techniques are described herein for performing optical flow estimation for one or more frames. For example, a process can include determining an optical flow prediction associated with a plurality of frames. The process can include determining a position of at least one feature associated with a first frame and determining, based on the position of the at least one feature in the first frame and the optical flow prediction, a position estimate of a search area for searching for the at least one feature in a second frame. The process can include determining, from within the search area, a position of the at least one feature in the second frame

公开(公告)号：US20220058450A1

公开(公告)日：2022-02-24

申请号：US17407046

申请日：2021-08-19

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Shizhong Steve HAN ,  Fatih Murat PORIKLI

IPC: G06K9/64 ,  G06F16/25 ,  G06T7/45

Abstract: Certain aspects of the present disclosure provide techniques for performing tabular convolution, including performing a tabularization operation on input data to generate a tabularized representation of the input data and performing a convolution operation using the tabularized representation of the input data to generate a convolution output.

公开(公告)号：US20220019873A1

公开(公告)日：2022-01-20

申请号：US17379833

申请日：2021-07-19

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Fatih Murat PORIKLI

IPC: G06N3/04 ,  G06N3/08

Abstract: In one aspect of the present disclosure, a method includes: determining a number of loops for a convolution layer of an elastic bottleneck block; for each loop of the number of loops: loading a loop-specific set of convolution weights; performing a convolution operation using the loop-specific set of convolution-weights; and storing loop-specific convolution results in a local memory; and determining an output of the convolution layer based on a summation of loop-specific convolution results associated with each loop of the number of loops.

公开(公告)号：US20210150306A1

公开(公告)日：2021-05-20

申请号：US17098049

申请日：2020-11-13

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Yang YANG ,  Parham NOORZAD

IPC: G06N3/02 ,  G06F17/15

Abstract: Aspects described herein provide a method of performing phase selective convolution, including: receiving multi-phase pre-activation activation data; partitioning the multi-phase pre-activation data; applying a first activation function to the set of first phase pre-activation data to form a set of first phase activation output; convolving the set of first phase activation output with a first convolution kernel to form a first phase output feature map; negating the set of second phase activation data; applying a second activation function to the negated set of second phase pre-activation data to form a set of second phase activation output; convolving the set of second phase activation output with a second convolution kernel to form a second phase output feature map; negating the second phase output feature map; and training the neural network based on the first phase output feature map and the second phase output feature map.