Nanxiang Li
Research Subjects
Research Interests
Nanxiang Li has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Arvind Kumar Shekar
Robert Bosch GmbH
1 shared publication - Axel Wendt
Robert Bosch GmbH, 70049 Stuttgart, Germany
1 shared publication - Liang Gou
Splunk Technology USA
1 shared publication - Lincan Zou
Robert Bosch Research and Technology Center, USA
1 shared publication - Liu Ren
Bosch Research North America & Bosch Center for Artificial Intelligence (BCAI)
1 shared publication - Michael Hofmann
Robert Bosch GmbH, Germany
1 shared publication
Latest Publications
- 20 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 27 (2) , 261-271
VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection
Traffic light detection is crucial for environment perception and decision-making in autonomous driving. State-of-the-art detectors are built upon deep Convolutional Neural Networks (CNNs) and have exhibited promising performance. However, one looming concern with CNN based detectors is how to thoroughly evaluate the performance of accuracy and robustness before they can be deployed to autonomous vehicles. In this work, we propose a visual analytics system, VATLD, equipped with a disentangled representation learning and semantic adversarial learning, to assess, understand, and improve the accuracy and robustness of traffic light detectors in autonomous driving applications. The disentangled representation learning extracts data semantics to augment human cognition with human-friendly visual summarization, and the semantic adversarial learning efficiently exposes interpretable robustness risks and enables minimal human interaction for actionable insights. We also demonstrate the effectiveness of various performance improvement strategies derived from actionable insights with our visual analytics system, VATLD, and illustrate some practical implications for safety-critical applications in autonomous driving.
- 20 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 27 (2) , 261-271
VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection
Traffic light detection is crucial for environment perception and decision-making in autonomous driving. State-of-the-art detectors are built upon deep Convolutional Neural Networks (CNNs) and have exhibited promising performance. However, one looming concern with CNN based detectors is how to thoroughly evaluate the performance of accuracy and robustness before they can be deployed to autonomous vehicles. In this work, we propose a visual analytics system, VATLD, equipped with a disentangled representation learning and semantic adversarial learning, to assess, understand, and improve the accuracy and robustness of traffic light detectors in autonomous driving applications. The disentangled representation learning extracts data semantics to augment human cognition with human-friendly visual summarization, and the semantic adversarial learning efficiently exposes interpretable robustness risks and enables minimal human interaction for actionable insights. We also demonstrate the effectiveness of various performance improvement strategies derived from actionable insights with our visual analytics system, VATLD, and illustrate some practical implications for safety-critical applications in autonomous driving.