Vision and Autonomous Systems Seminar

  • Gates Hillman Centers
  • Traffic21 Classroom 6501

Towards Weakly-Supervised Visual Understanding

Learning with weak and self-supervisions recently emerged as compelling tools towards leveraging vast amounts of unlabeled or partially-labeled data. In this talk, I will present some of the latest advances in weakly-supervised visual scene understanding from NVIDIA. Specifically, I will summarize and discuss some challenges and potential solutions in weakly-supervised learning, and introduce our works mainly from three directions: 1. learning with Inaccurate supervision, 2. learning with Incomplete supervision, and 3. learning with Inexact supervision. I will talk about specific works and applications that are aligned with these directions, including semantic boundary detection under noisy annotations, unsupervised domain adaptation, person re-id and weakly-supervised object detection, with their applications in autonomous driving, robotics, medical imaging and AI city.

Zhiding Yu joined NVIDIA Research as a Research Scientist in 2018. Before that, he obtained Ph.D. degree in ECE from Carnegie Mellon University in 2017. His research interests mainly focus on deep representation learning, weakly/semi-supervised learning, transfer learning and deep structured prediction, with their applications to: (1) general scene/video understanding, (2) bottom-up perceptual grouping and mid-level vision, (3) robust representation for cross-domain/cross-task/open-set generalization and adaptation, (4) learning with interactive weak supervisions. He is a winner of the Domain Adaptation for Semantic Segmentation Challenge in Workshop on Autonomous Driving (WAD), CVPR18. He is a co-author of the best student paper in ISCSLP14, and the winner of the best paper award in WACV15. He was twice the recipient of the HKTIIT Post-Graduate Excellence Scholarships in 2010 and 2012. His intern work on deep facial expression recognition at Microsoft Research won first runner-up at the EmotiW-SFEW Challenge 2015 and was integrated into the Microsoft Emotion Recognition API under the Microsoft Azure Cognitive Services.

Sponsored in part by Facebook Reality Labs Pittsburgh

For More Information, Please Contact: