An Evaluation of Zero-Cost Proxies - from Neural Architecture Performance to Model Robustness
Jovita Lukasik,Michael Moeller, Margret Keuper
Published in International Journal of Computer Vision, 2024
[pdf] [github] [bibtex]
Publications
2024
Surprisingly Strong Performance Prediction with Neural Graph Features
Gabriela Kadlecová, Jovita Lukasik, Martin Pilát, Petra Vidnerová, Mahmoud Safari, Roman Neruda, Frank Hutter
Published in Proceedings of the 41st International Conference on Machine Learning, 2024
[pdf] [github] [bibtex]
Implicit Representations for Constrained Image Segmentation
Jan Philipp Schneider, Mishal Fatima, Jovita Lukasik, Andreas Kolb, Margret Keuper, Michael Moeller
Published in Proceedings of the 41st International Conference on Machine Learning, 2024
[pdf] [github] [bibtex]
2023
Improving Native CNN Robustness with Filter Frequency Regularization
Jovita Lukasik, Paul Gavrikov, Janis Keuper, Margret Keuper
Published in Transactions on Machine Learning Research, 2023
[pdf] [github] [bibtex]
Implicit Representations for Image Segmentation
Jan Philipp Schneider, Mishal Fatima, Jovita Lukasik, Andreas Kolb, Margret Keuper, Michael Moeller
Published in Unireps@NeurIPS 2023, 2023
[pdf] [bibtex]
An Evaluation of Zero-Cost Proxies - from Neural Architecture Performance to Model Robustness (oral)
Jovita Lukasik,Michael Moeller, Margret Keuper
Published in DAGM German Conference on Pattern Recognition, 2023
[pdf] [arxiv] [github] [bibtex]
Differentiable Architecture Search: a One-Shot Method?
Jovita Lukasik, Jonas Geiping, Michael Moeller, Margret Keuper
Published in AutoML Conference 2023 Workshops, 2023
[pdf] [bibtex]
Neural Architecture Design and Robustness: A Dataset
Steffen Jung, Jovita Lukasik, Margret Keuper
Published in The Eleventh International Conference on Learning Representations, 2023
[pdf] [arxiv] [github] [bibtex]
2022
Learning Where to Look – Generative NAS Is Surprisingly Efficient
Jovita Lukasik, Steffen Jung, Margret Keuper
Published in European Conference on Computer Vision, 2022
[pdf] [arxiv] [github] [bibtex]
Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks
Arber Zela, Julien Niklas Siems, Lucas Zimmer, Jovita Lukasik, Margret Keuper, Frank Hutter
Published in The Tenth International Conference on Learning Representations, 2022
[pdf] [arxiv] [bibtex]
2021
DARTS for Inverse Problems: a Study on Stability
Jonas Geiping, Jovita Lukasik, Margret Keuper, Michael Moeller
Published in NeurIPS 2021 Deep Inverse Workshop, 2021
[pdf] [poster] [bibtex]
Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
Jovita Lukasik, David Friede, Arber Zela, Frank Hutter, Margret Keuper
Published in International Joint Conference on Neural Networks, 2021
[pdf] [arxiv] [github] [bibtex]
2020
Neural Architecture Performance Prediction Using Graph Neural Networks
Jovita Lukasik, David Friede, Heiner Stuckenschmidt, Margret Keuper
Published in DAGM German Conference on Pattern Recognition, 2020
[pdf] [arxiv] [github] [bibtex]