2 citations · 5 across the 8 of their papers we have counts for
6 papers · 1 filter
Structure over Pixels: Learning Variable-Length Visual Programs
Piotr Wyrwiński, Kacper Dobek, Krzysztof Krawiec
Discrete visual tokenizers map images to ordered sequences of tokens, providing a natural representation for structural scene descriptions. Most use a fixed sequence length, while…
Self-Distilling Generative Adversarial Networks
Antoni Nowinowski, Krzysztof Krawiec
In modern GANs, maintaining an Exponential Moving Average (EMA) of the generator's weights is a standard practice, as such an averaged model consistently outperforms the actively t…
Modeling Retinal Ganglion Cells with Neural Differential Equations
Kacper Dobek, Daniel Jankowski, Krzysztof Krawiec
This work explores Liquid Time-Constant Networks (LTCs) and Closed-form Continuous-time Networks (CfCs) for modeling retinal ganglion cell activity in tiger salamanders across thre…
Generative Learning of Differentiable Object Models for Compositional Interpretation of Complex Scenes
Antoni Nowinowski, Krzysztof Krawiec
This study builds on the architecture of the Disentangler of Visual Priors (DVP), a type of autoencoder that learns to interpret scenes by decomposing the perceived objects into in…
Autoassociative Learning of Structural Representations for Modeling and Classification in Medical Imaging
Zuzanna Buchnajzer, Kacper Dobek, Stanisław Hapke +2
Deep learning architectures based on convolutional neural networks tend to rely on continuous, smooth features. While this characteristics provides significant robustness and prove…
Disentangling Visual Priors: Unsupervised Learning of Scene Interpretations with Compositional Autoencoder
Krzysztof Krawiec, Antoni Nowinowski
Contemporary deep learning architectures lack principled means for capturing and handling fundamental visual concepts, like objects, shapes, geometric transforms, and other higher-…