This material is based upon work supported by the U.S. Department of Homeland Security, Science and Technology Directorate, under Grant Award 70RSAT18FR0000141. . The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of the U.S. Department of Homeland Security. [12/2013] Machine Learning for Video Tracking of Passengers and Divested Objects at the Checkpoint Henry Medeiros, Marquette University [email protected]
12
Embed
Machine Learning for Video Tracking of Passengers and ...Convolutional Pose Machine [1] Mask R-CNN [2] [1] Shih-En, Ramakrishna, Kanade, Sheikh. "Convolutional pose machines." IEEE
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
This material is based upon work supported by the U.S. Department of Homeland Security, Science and Technology Directorate, under Grant Award
70RSAT18FR0000141. . The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily
representing the official policies, either expressed or implied, of the U.S. Department of Homeland Security. [12/2013]
[6] Kendall, Gal, Cipolla "Multi-task learning using uncertainty to weigh losses for scene geometry and semantics" IEEE Conf. on Computer Vision and Pattern Recognition 2018
Network predictions are not confidence estimates [5]
Neural networks don’t know what they don’t know
[5] Gal, Ghahramani "Dropout as a Bayesian approximation: Representing model uncertainty in deep learning" International Conference on Machine Learning 2016
Training data Predictions with unjustified high confidence
Use multiple predictions to correct high-confidence mistakes
E.g., semantic segmentation refinement [8]
Estimating uncertainty with Monte Carlo sampling
[8] Dias, Medeiros "Semantic segmentation refinement by Monte Carlo region growing of high confidence detections" Asian Conference on Computer Vision 2018
Train the network to explicitly predict the uncertainty
E.g., uncertainty-aware gaze estimation [9]
Uncertainty learning
[9] Dias, Malafronte, Medeiros, Odone "Gaze Estimation for Assisted Living Environments" IEEE Winter Conference on Applications of Computer Vision 2019