Showing 2023Show all
2 papers · 1 filter
cs.CV2023
Class Balanced Dynamic Acquisition for Domain Adaptive Semantic Segmentation using Active Learning
Marc Schachtsiek, Simone Rossi, Thomas Hannagan
Domain adaptive active learning is leading the charge in label-efficient training of neural networks. For semantic segmentation, state-of-the-art models jointly use two criteria of…
stat.ML2023
On permutation symmetries in Bayesian neural network posteriors: a variational perspective
Simone Rossi, Ankit Singh, Thomas Hannagan
The elusive nature of gradient-based optimization in neural networks is tied to their loss landscape geometry, which is poorly understood. However recent work has brought solid evi…