Zhiding Yu – NVIDIA Technical Blog News and tutorials for developers, data scientists, and IT admins 2025-01-09T20:50:58Z http://www.open-lab.net/blog/feed/ Zhiding Yu https://chrisding.github.io/ <![CDATA[End-to-End Driving at Scale with Hydra-MDP]]> http://www.open-lab.net/blog/?p=84173 2024-08-21T21:47:07Z 2024-06-17T14:48:47Z Building an autonomous system to navigate the complex physical world is extremely challenging. The system must perceive its environment and make quick, sensible...]]>

Building an autonomous system to navigate the complex physical world is extremely challenging. The system must perceive its environment and make quick, sensible decisions. Passenger experience is also important and includes acceleration, curvature, smoothness, road adherence, and time-to-collision. In this post, we introduce Hydra-MDP, an innovative framework that advances the field of end-to…

Source

]]>
Zhiding Yu https://chrisding.github.io/ <![CDATA[Segment Objects without Masks and Reduce Annotation Effort Using the DiscoBox DL Framework]]> http://www.open-lab.net/blog/?p=45220 2023-10-20T18:03:35Z 2022-03-24T14:00:00Z Instance segmentation is a core visual recognition problem for detecting and segmenting objects. In the past several years, this area has been one of the holy...]]>

Instance segmentation is a core visual recognition problem for detecting and segmenting objects. In the past several years, this area has been one of the holy grails in the computer vision community with wide applications ranging from autonomous vehicles (AV), robotics, video analysis, smart home, digital human, and healthcare. Annotation, the process of classifying every object in an image…

Source

]]>
0
Zhiding Yu https://chrisding.github.io/ <![CDATA[Building a Benchmark for Human-Level Concept Learning and Reasoning]]> http://www.open-lab.net/blog/?p=22299 2025-01-09T20:50:58Z 2020-11-17T22:31:00Z Humans have an inherent ability to learn novel concepts from only a few samples and generalize these concepts to different situations. Even though today��s...]]>

Humans have an inherent ability to learn novel concepts from only a few samples and generalize these concepts to different situations. Even though today’s machine learning models excel with an abundance of training data on standard recognition tasks, a considerable gap exists between machine-level pattern recognition and human-level concept learning. Over 50 years ago, M. M. Bongard…

Source

]]>
1
���˳���97caoporen����