Invention Application
- Patent Title: DEEP NEURAL NETWORK COLOR SPACE OPTIMIZATION
-
Application No.: US16527954Application Date: 2019-07-31
-
Publication No.: US20210035331A1Publication Date: 2021-02-04
- Inventor: Xiufeng XIE , Kyu-Han KIM
- Applicant: Hewlett Packard Enterprise Development LP
- Applicant Address: US TX Houston
- Assignee: Hewlett Packard Enterprise Development LP
- Current Assignee: Hewlett Packard Enterprise Development LP
- Current Assignee Address: US TX Houston
- Main IPC: G06T9/00
- 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.
Public/Granted literature
- US11049286B2 Deep neural network color space optimization Public/Granted day:2021-06-29
Information query