Search Results for author:
Found 6 papers, 0 papers with code
Domain Adversarial Training: A Game Perspective
Defining optimal solutions in domain-adversarial training as a local Nash equilibrium, we show that gradient descent in domain-adversarial training can violate the asymptotic convergence guarantees of the optimizer, oftentimes hindering the transfer performance.
Low-Budget Active Learning via Wasserstein Distance: An Integer Programming Approach
Active learning is the process of training a model with limited labeled data by selecting a core subset of an unlabeled data pool to label.
Ultrahyperbolic Neural Networks
The lack of geodesic between every pair of ultrahyperbolic points makes the task of learning parametric models (e. g., neural networks) difficult.
f-Domain-Adversarial Learning: Theory and Algorithms for Unsupervised Domain Adaptation with Neural Networks
We provide empirical results for several f-divergences and show that some, not considered previously in domain-adversarial learning, achieve state-of-the-art results in practice.
Sim2SG: Sim-to-Real Scene Graph Generation for Transfer Learning
However, neural network models trained on synthetic data, do not perform well on real data because of the domain gap.
Lorentzian Distance Learning
This formulation produces node representations close to the centroid of their descendants.
