Sustainable and Interpretable Neural Networks Group
We are a research group at the Jagiellonian University in Kraków. Our work is focused on the development of interpretable-by-design algorithms in the field of computer vision. We emphasize the importance of the approaches based on cognitive theories and pay special attention to their intuitiveness and sustainability. We aim to provide trustworthy methods that can be easily adopted in the industry.
Achievements
ProtoNCD: Prototypical Parts for Interpretable Novel Class Discovery
Tomasz Michalski, Dawid Rymarczyk, Daniel Barczyk, Bartosz Zieliński
ESANN 2024
Revisiting FunnyBirds evaluation framework for prototypical parts networks (paper)
Szymon Opłatek, Dawid Rymarczyk, Bartosz Zieliński
xAI 2024
Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations (paper)
Mikołaj Sacha, Bartosz Jura, Dawid Rymarczyk, Łukasz Struski, Jacek Tabor, Bartosz Zieliński
AAAI 2024
ICICLE: Interpretable Class Incremental Continual Learning (paper)
Dawid Rymarczyk, Joost van de Weijer, Bartosz Zieliński, Bartłomiej Twardowski
ICCV 2023
OPUS (grant)
National Science Center, Poland
2023 – 2026
Title: Interpretable and sustainable artificial intelligence with intuitive explanations
Number: 2022/47/B/ST6/03397
Principal investigator: Bartosz Zieliński
ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts (paper)
Mikołaj Sacha , Dawid Rymarczyk , Łukasz Struski , Jacek Tabor , Bartosz Zieliński
WACV 2023
PRELUDIUM 21 (grant)
National Science Center, Poland
2023 – 2024
Title: Improving interpretability in deep neural networks
Number: 2022/45/N/ST6/04147
Principal investigator: Dawid Rymarczyk
Interpretable image classification with differentiable prototypes assignment (paper)
Dawid Rymarczyk, Łukasz Struski, Michał Górszczak, Koryna Lewandowska, Jacek Tabor, Bartosz Zieliński
ECCV 2022
ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification (paper)
Dawid Rymarczyk, Adam Pardyl, Jarosław Kraus, Aneta Kaczyńska, Marek Skomorowski, Bartosz Zieliński
ECML PKDD 2022
ProtoPShare: Prototypical Parts Sharing for Similarity Discovery in Interpretable Image Classification (paper)
Dawid Rymarczyk, Łukasz Struski, Jacek Tabor, Bartosz Zieliński
KDD 2021
Posts
Algorytmy w codziennym życiu: zrozumieć czy zaufać?
Wpływ algorytmów na codzienne decyzje Informacje, na których opieramy się w swoich codziennych wyborach zawodowych, ekonomicznych a nawet światopoglądowych coraz częściej trafiają do nas dzięki wszechobecnym już algorytmom. Chociaż korzystamy z wyselekcjonowanych...