Dropout Sampling for Robust Object Detection in Open-Set Conditions.
Dimity MillerLachlan NicholsonFeras DayoubNiko SünderhaufPublished in: CoRR (2017)
Keyphrases
- object detection
- real world conditions
- sufficient conditions
- random sampling
- computationally efficient
- object recognition
- real time
- face detection
- object classification
- parameter tuning
- feature space
- active learning
- probabilistic model
- multi class
- decision trees
- monte carlo
- partial occlusion
- computer vision
- sampled data
- neural network