2019 · 119 citations · 34 references
ComputingComputer ScienceComputer VisionKnowledge TransferMachine LearningDeep LearningImitation LearningPose EstimationScene UnderstandingTransfer LearningVisual OdometryHigh-level Intermediate RepresentationKnowledge DistillationKnowledge Transfer Evaluation
This paper presents a novel method to distill knowledge from a deep pose regressor network for efficient Visual Odometry (VO). Standard distillation relies on ''dark knowledge'' for successful knowledge transfer. As this knowledge is not available in pose regression and the teacher prediction is not always accurate, we propose to emphasize the knowledge transfer only when we trust the teacher. We achieve this by using teacher loss as a confidence score which places variable relative importance on the teacher prediction. We inject this confidence score to the main training task via Attentive Imitation Loss (AIL) and when learning the intermediate representation of the teacher through Attentive Hint Training (AHT) approach. To the best of our knowledge, this is the first work which successfully distill the knowledge from a deep pose regression network. Our evaluation on the KITTI and Malaga dataset shows that we can keep the student prediction close to the teacher with up to 92.95% parameter reduction and 2.12x faster in computation time.
34
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Are we ready for autonomous driving? The KITTI vision benchmark suite
Andreas Geiger, P Lenz, R. Urtasun · 2012 · 14.4K citations
Distilling the Knowledge in a Neural Network
Geoffrey E. Hinton, Oriol Vinyals · arXiv (Cornell University) · 2015 · 14K citations · Full text
FlowNet: Learning Optical Flow with Convolutional Networks
Alexey Dosovitskiy, Philipp Fischer, Eddy Ilg et al. · 2015 · 4.2K citations
A benchmark for the evaluation of RGB-D SLAM systems
Jrgen Sturm, Nikolas Engelhard, Felix Endres et al. · 2012 · 3.9K citations