4 papers
ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts
MikoÅaj Sacha, Dawid Rymarczyk, Åukasz Struski +2
We introduce ProtoSeg, a novel model for interpretable semantic image segmentation, which constructs its predictions using similar patches from the training set. To achieve accurac…
SONG: Self-Organizing Neural Graphs
Åukasz Struski, Tomasz Danel, Marek Åmieja +2
Recent years have seen a surge in research on deep interpretable neural networks with decision trees as one of the most commonly incorporated tools. There are at least three advant…
MultiPlaneNeRF: Neural Radiance Field with Non-Trainable Representation
Dominik Zimny, Artur Kasymov, Adam Kania +4
NeRF is a popular model that efficiently represents 3D objects from 2D images. However, vanilla NeRF has some important limitations. NeRF must be trained on each object separately.…
Bounding Evidence and Estimating Log-Likelihood in VAE
Åukasz Struski, Marcin Mazur, PaweÅ 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…