3 papers
cs.LG2024
HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learning
Patryk Krukowski, Anna Bielawska, Kamil Książek +3
Recently, a new Continual Learning (CL) paradigm was presented to control catastrophic forgetting, called Interval Continual Learning (InterContiNet), which relies on enforcing int…
cs.CV2024
HyperPlanes: Hypernetwork Approach to Rapid NeRF Adaptation
Paweł Batorski, Dawid Malarz, Marcin Przewięźlikowski +3
Neural radiance fields (NeRFs) are a widely accepted standard for synthesizing new 3D object views from a small number of base images. However, NeRFs have limited generalization pr…
cs.LG2022
Bounding Evidence and Estimating Log-Likelihood in VAE
Łukasz Struski, Marcin Mazur, Paweł Batorski +2
Many crucial problems in deep learning and statistical inference are caused by a variational gap, i.e., a difference between model evidence (log-likelihood) and evidence lower boun…