TY - UNPB
T1 - Learning invariant representations of planar curves
AU - Pai, Gautam
AU - Wetzler, Aaron
AU - Kimmel, Ron
N1 - Publisher Copyright: © ICLR 2019 - Conference Track Proceedings. All rights reserved.; 5th International Conference on Learning Representations, ICLR 2017 ; Conference date: 24-04-2017 Through 26-04-2017
PY - 2017
Y1 - 2017
N2 - We propose a metric learning framework for the construction of invariant geometric functions of planar curves for the Euclidean and Similarity group of transformations. We leverage on the representational power of convolutional neural networks to compute these geometric quantities. In comparison with axiomatic constructions, we show that the invariants approximated by the learning architectures have better numerical qualities such as robustness to noise, resiliency to sampling, as well as the ability to adapt to occlusion and partiality. Finally, we develop a novel multi-scale representation in a similarity metric learning paradigm.
AB - We propose a metric learning framework for the construction of invariant geometric functions of planar curves for the Euclidean and Similarity group of transformations. We leverage on the representational power of convolutional neural networks to compute these geometric quantities. In comparison with axiomatic constructions, we show that the invariants approximated by the learning architectures have better numerical qualities such as robustness to noise, resiliency to sampling, as well as the ability to adapt to occlusion and partiality. Finally, we develop a novel multi-scale representation in a similarity metric learning paradigm.
UR - https://openreview.net/forum?id=BymIbLKgl
U2 - 10.48550/arXiv.1611.07807
DO - 10.48550/arXiv.1611.07807
M3 - Preprint
BT - Learning invariant representations of planar curves
PB - International Conference on Learning Representations
ER -