Signals, Waves, and Learning: A Data-Driven Paradigm for Wave-Based Inverse Problems

Project Information

SWING

Grant agreement ID: 852821

DOI 10.3030/852821

EC signature date 30 October 2019

Start date 1 January 2020

End date 31 December 2024

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost € 1 986 430,00

EU contribution € 1 986 430,00

Coordinated by

UNIVERSITAT BASEL
Switzerland

Publications

Conference proceedings (9)

Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows

Author(s): Michael Puthawala, Matti Lassas, Ivan Dokmanic, Maarten De Hoop
Published in: Proceedings of the 39th International Conference on Machine Learning, 2022
Publisher: PMLR

Neural Link Prediction with Walk Pooling

Author(s): Liming Pan, Cheng Shi, Ivan Dokmanic
Published in: International Conference on Learning Representations, 2022
Publisher: Tenth International Conference on Learning Representations

Universal Approximation Under Constraints is Possible with Transformers

Author(s): Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanic
Published in: International Conference on Learning Representations, 2022
Publisher: ICLR

Truly Shift-Invariant Convolutional Neural Networks

Author(s): Anadi Chaman, Ivan Dokmanic
Published in: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Publisher: IEEE

Trumpets: Injective Flows for Inference and Inverse Problems

Author(s): Kothari, Konik; Khorashadizadeh, AmirEhsan; de Hoop, Maarten; Dokmanić, Ivan
Published in: Conference on Uncertainty in Artificial Intelligence (UAI), 2021
Publisher: NA

Implicit Neural Representation for Mesh-Free Inverse Obstacle Scattering

Author(s): Tin Vlašić, Hieu Nguyen, Ivan Dokmanić
Published in: Asilomar Conference on Signals, Systems, and Computers, 2022
Publisher: NA

Truly shift-equivariant convolutional neural networks with adaptive polyphase upsampling

Author(s): Anadi Chaman, Ivan Dokmanić
Published in: 2021 55th Asilomar Conference on Signals, Systems, and Computers, 2021
Publisher: IEEE

Manifold Rewiring for Unlabeled Imaging

Author(s): Valentin Debarnot, Vinith Kishore, Cheng Shi, Ivan Dokmanic
Published in: APSIPA, 2022
Publisher: IEEE

Learning the Geometry of Wave-Based Imaging

Author(s): Konik Kothari, Maarten de Hoop, Ivan Dokmanić
Published in: Advances in Neural Information Processing Systems, Issue 33, 2020
Publisher: Advances in Neural Information Processing Systems

Peer reviewed articles (4)

Learning Multiscale Convolutional Dictionaries for Image Reconstruction

Author(s): Tianlin Liu, Anadi Chaman, David Belius, Ivan Dokmanić
Published in: IEEE Transactions on Computational Imaging, 2022, ISSN 2333-9403
Publisher: IEEE

Learning sub-patterns in piecewise continuous functions

Author(s): Kratsios, Anastasis; Zamanlooy, Behnoosh
Published in: Neurocomputing, Issue 09252312, 2022, ISSN 0925-2312
Publisher: Elsevier BV
DOI: 10.1016/j.neucom.2022.01.036

Globally Injective ReLU Networks

Author(s): Michael Puthawala, Konik Kothari, Matti Lassas, Ivan Dokmanić, Maarten de Hoop
Published in: Journal of Machine Learning Research, 2022, ISSN 1532-4435
Publisher: MIT Press

Total Least Squares Phase Retrieval

Author(s): Sidharth Gupta, Ivan Dokmanić
Published in: IEEE Transactions on Signal Processing, 2021, ISSN 1941-0476
Publisher: IEEE

Other (2)

Conditional Injective Flows for Bayesian Imaging

Author(s): AmirEhsan Khorashadizadeh, Konik Kothari, Leonardo Salsi, Ali Aghababaei Harandi, Maarten de Hoop, Ivan Dokmanić
Published in: 2022
Publisher: NA

Orthogonal Matrix Retrieval with Spatial Consensus for 3D Unknown-View Tomography

Author(s): Shuai Huang, Mona Zehni, Ivan Dokmanic, Zhizhen Zhao
Published in: arXiv, 2022
Publisher: NA