Xun Xu

Title: Xun Xu: Innovator in Semantic Segmentation Technologies

Introduction

Xun Xu is a prominent inventor based in Mountain View, CA, known for his contributions to the field of semantic segmentation. With a focus on enhancing image processing techniques, he has developed innovative methods that leverage convolutional neural networks.

Latest Patents

Xun Xu holds 2 patents that showcase his expertise in semantic segmentation. His latest patents include:

1. **Method and System of Annotation Densification for Semantic Segmentation**: This patent discloses methods for obtaining image information and coarse annotation information. It involves performing an image matting operation and applying a trained Convolutional Neural Network (ConvNet) model to generate fine semantic segmentation annotation information.

2. **Method and System for Semantic Segmentation Involving Multi-Task Convolutional Neural Network**: This patent describes a method that employs multi-task convolutional networks with curriculum-based transfer learning. It includes training a semantic segmentation decoder network and generating both semantic and instance segmentation maps in a single feedforward pass.

Career Highlights

Xun Xu has worked with notable companies such as Didi Research America, LLC and Beijing Didi Infinity Technology and Development Co., Ltd. His experience in these organizations has contributed to his development of advanced technologies in the field of image processing.

Collaborations

Xun Xu has collaborated with Ruxiao Bao, further enhancing his work in semantic segmentation technologies.

Conclusion

Xun Xu's innovative contributions to semantic segmentation through his patents and career experiences highlight his significant role in advancing image processing technologies. His work continues to influence the field and pave the way for future developments.