121 citations · 416 across the 9 of their papers we have counts for
11 papers
ProPML: Probability Partial Multi-label Learning
Łukasz Struski, Adam Pardyl, Jacek Tabor +1
Partial Multi-label Learning (PML) is a type of weakly supervised learning where each training instance corresponds to a set of candidate labels, among which only some are true. In…
Classifying bacteria clones using attention-based deep multiple instance learning interpreted by persistence homology
Adriana Borowa, Dawid Rymarczyk, Dorota Ochońska +2
In this work, we analyze if it is possible to distinguish between different clones of the same bacteria species (Klebsiella pneumoniae) based only on microscopic images. It is a ch…
ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery
Dawid Rymarczyk, Łukasz Struski, Jacek Tabor +1
In this paper, we introduce ProtoPShare, a self-explained method that incorporates the paradigm of prototypical parts to explain its predictions. The main novelty of the ProtoPShar…
Deep learning approach to describe and classify fungi microscopic images
Bartosz Zieliński, Agnieszka Sroka-Oleksiak, Dawid Rymarczyk +2
Preliminary diagnosis of fungal infections can rely on microscopic examination. However, in many cases, it does not allow unambiguous identification of the species by microbiologis…
Deep learning approach to description and classification of fungi microscopic images
Bartosz Zieliński, Agnieszka Sroka-Oleksiak, Dawid Rymarczyk +2
Diagnosis of fungal infections can rely on microscopic examination, however, in many cases, it does not allow unambiguous identification of the species due to their visual similari…
Persistence Bag-of-Words for Topological Data Analysis
Bartosz Zieliński, Michał Lipiński, Mateusz Juda +2
Persistent homology (PH) is a rigorous mathematical theory that provides a robust descriptor of data in the form of persistence diagrams (PDs). PDs exhibit, however, complex struct…
Processing of missing data by neural networks
Marek Smieja, Łukasz Struski, Jacek Tabor +2
We propose a general, theoretically justified mechanism for processing missing data by neural networks. Our idea is to replace typical neuron's response in the first hidden layer b…
Cascade context encoder for improved inpainting
Bartosz Zieliński, Łukasz Struski, Marek Śmieja +1
In this paper, we analyze if cascade usage of the context encoder with increasing input can improve the results of the inpainting. For this purpose, we train context encoder for 64…
Persistence Codebooks for Topological Data Analysis
Bartosz Zielinski, Michal Lipinski, Mateusz Juda +2
Persistent homology (PH) is a rigorous mathematical theory that provides a robust descriptor of data in the form of persistence diagrams (PDs) which are 2D multisets of points. The…
A Study on Topological Descriptors for the Analysis of 3D Surface Texture
Matthias Zeppelzauer, Bartosz Zielinski, Mateusz Juda +1
Methods from computational topology are becoming more and more popular in computer vision and have shown to improve the state-of-the-art in several tasks. In this paper, we investi…
Topological descriptors for 3D surface analysis
Matthias Zeppelzauer, Bartosz Zieliński, Mateusz Juda +1
We investigate topological descriptors for 3D surface analysis, i.e. the classification of surfaces according to their geometric fine structure. On a dataset of high-resolution 3D…