Peng Tang

Title: Innovations of Peng Tang in Object Detection

Introduction

Peng Tang is an accomplished inventor based in Mountain View, CA. He has made significant contributions to the field of object detection through his innovative methods. His work focuses on enhancing the capabilities of neural networks in identifying objects within images.

Latest Patents

Peng Tang holds a patent for a method titled "Proposal learning for semi-supervised object detection." This patent describes a technique for generating a neural network that detects one or more objects in images. The method involves creating self-supervised proposal learning losses based on proposal features and their predictions. Additionally, it generates consistency-based proposal learning losses from noisy predictions and corresponding noise-free predictions. The combined loss from these two types of learning losses is used to update the neural network, improving its accuracy in object detection.

Career Highlights

Currently, Peng Tang is employed at Salesforce.com, Inc., where he continues to develop innovative solutions in the tech industry. His expertise in neural networks and object detection has positioned him as a valuable asset to his team and the company.

Collaborations

Some of his notable coworkers include Chetan Ramaiah and Caiming Xiong. Their collaborative efforts contribute to the advancement of technology in their respective fields.

Conclusion

Peng Tang's work in object detection exemplifies the innovative spirit of modern technology. His contributions are paving the way for more advanced applications in artificial intelligence and machine learning.