Adding star-convexity hinge losses during training makes a model's loss landscape bowl-shaped around the ground truth and improves iterative predictions on RNN, point cloud registration, and image alignment tasks.
Deep neural networks on diffeomorphism groups for optimal shape reparameterization
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
One of the fundamental problems in shape analysis is to align curves or surfaces before computing geodesic distances between their shapes. Finding the optimal reparametrization realizing this alignment is a computationally demanding task, typically done by solving an optimization problem on the diffeomorphism group. In this paper, we propose an algorithm for constructing approximations of orientation-preserving diffeomorphisms by composition of elementary diffeomorphisms. The algorithm is implemented using PyTorch, and is applicable for both unparametrized curves and surfaces. Moreover, we show universal approximation properties for the constructed architectures, and obtain bounds for the Lipschitz constants of the resulting diffeomorphisms.
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Loss Convexification for Learning Iterative Models
Adding star-convexity hinge losses during training makes a model's loss landscape bowl-shaped around the ground truth and improves iterative predictions on RNN, point cloud registration, and image alignment tasks.