公开(公告)号：US20210035330A1

公开(公告)日：2021-02-04

申请号：US16526335

申请日：2019-07-30

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Xiufeng XIE ,  Kyu-Han KIM

IPC: G06T9/00 ,  G06N3/04 ,  G06N5/04 ,  G06F17/14

Abstract: Example method includes: transmit a plurality of probe images from an Internet of Things (IoT) device at an edge network to a server hosting a target deep neural network (DNN), wherein the plurality of images are injected with a limited amount of noise; receive a feedback comprising a plurality of discrete cosine transform (DCT) coefficients from the server hosting the target DNN, wherein the plurality of DCT coefficients are unique to the target DNN; generate a quantization table based on the feedback received from the server hosting the target DNN; compress a set of real-time images using the generated quantization table by the IoT device at the edge network; and transmit the compressed set of real-time images to the server hosting the target DNN for DNN inferences.

公开(公告)号：US20210035331A1

公开(公告)日：2021-02-04

申请号：US16527954

申请日：2019-07-31

Applicant: Hewlett Packard Enterprise Development LP

Inventor： Xiufeng XIE ,  Kyu-Han KIM

IPC: G06T9/00 ,  H04N1/60 ,  G06T5/00

Abstract: Example method includes: transmitting a plurality of probe images from an IoT device at an edge network to a server hosting a target DNN, wherein the plurality of images are injected with a limited amount of noise to probe sensitivities of the target DNN to the red, green, and blue colors; receiving a feedback comprising a plurality of DCT coefficients unique to target DNN from the server hosting the target DNN; computing a plurality of color conversion weights based on the feedback received from the server; converting a set of real-time images from RGB color space to YUV color space using the plurality of color conversion weights unique to the target DNN; compressing the set of real-time images using a quantization table unique to the target DNN by the IoT device; and transmitting the compressed set of real-time images to the server hosting the target DNN for DNN inferences.