Xiufeng Xie

Title: Innovations by Xiufeng Xie

Introduction

Xiufeng Xie is an accomplished inventor based in Palo Alto, California. He has made significant contributions to the field of deep neural networks and image processing. With a total of 2 patents, his work focuses on optimizing color spaces and enhancing image compression techniques.

Latest Patents

Xiufeng Xie's latest patents include "Deep Neural Network Color Space Optimization" and "Image Compression with Bounded Deep Neural Network Perception Loss." The first patent describes a method that involves transmitting a plurality of probe images from an IoT device to a server hosting a target deep neural network (DNN). This method includes injecting a limited amount of noise into the images to probe the sensitivities of the DNN to red, green, and blue colors. The process continues with receiving feedback comprising DCT coefficients unique to the target DNN, computing color conversion weights, and converting real-time images from RGB to YUV color space. The final steps involve compressing these images and transmitting them back to the server for DNN inferences.

The second patent outlines a similar process, where a plurality of probe images is transmitted from an IoT device to a server. This method also includes injecting noise and receiving feedback in the form of DCT coefficients. The generated quantization table is then used to compress real-time images before they are sent back to the server for DNN inferences.

Career Highlights

Xiufeng Xie is currently employed at Hewlett Packard Enterprise Development LP, where he continues to innovate in the field of technology. His work has been instrumental in advancing the capabilities of deep learning applications.

Collaborations

Xiufeng collaborates with Kyu-Han Kim, a talented woman in the field, contributing to various projects that enhance their research and development efforts.

Conclusion

Xiufeng Xie's contributions to deep neural networks and image processing demonstrate his innovative spirit and commitment to advancing technology. His patents reflect a deep understanding of complex systems and a drive to improve real-time image processing techniques.