76 citations · 257 across the 98 of their papers we have counts for
7 papers · 1 filter
HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks
Filip Szatkowski, Karol J. Piczak, Przemysław Spurek +2
Implicit neural representations (INRs) are a rapidly growing research field, which provides alternative ways to represent multimedia signals. Recent applications of INRs include im…
Hypernetwork approach to Bayesian MAML
Piotr Borycki, Piotr Kubacki, Marcin Przewięźlikowski +3
The main goal of Few-Shot learning algorithms is to enable learning from small amounts of data. One of the most popular and elegant Few-Shot learning approaches is Model-Agnostic M…
Continual Learning with Guarantees via Weight Interval Constraints
Maciej Wołczyk, Karol J. Piczak, Bartosz Wójcik +5
We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. Contemporary Continual Learning (CL) methods focus…
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…
Points2NeRF: Generating Neural Radiance Fields from 3D point cloud
Dominik Zimny, Joanna Waczyńska, Tomasz Trzciński +1
Contemporary registration devices for 3D visual information, such as LIDARs and various depth cameras, capture data as 3D point clouds. In turn, such clouds are challenging to be p…
HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks
M. Przewięźlikowski, P. Przybysz, J. Tabor +2
The aim of Few-Shot learning methods is to train models which can easily adapt to previously unseen tasks, based on small amounts of data. One of the most popular and elegant Few-S…