Going Deep and Blind with Internal Statistics

Informazioni relative al progetto

DeepInternal

ID dell’accordo di sovvenzione: 788535

DOI

10.3030/788535

Progetto chiuso

Data della firma CE 24 Aprile 2018

Data di avvio 1 Maggio 2018

Data di completamento 31 Ottobre 2023

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 2 466 940,00

Contributo UE

€ 2 466 940,00

Coordinato da

WEIZMANN INSTITUTE OF SCIENCE
Israel

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Peer reviewed articles (2)

Self-Supervised Natural Image Reconstruction and Rich Semantic Classification from Brain Activity

Autori: Guy Gaziv; Roman Beliy; Niv Granot; Assaf Hoogi; Francesca Strappini; Tal Golan; Michal Irani
Pubblicato in: NeuroImage, Numero 4, 2022, ISSN 1053-8119
Editore: Academic Press
DOI: 10.1101/2020.09.06.284794

Convergent evolution of face spaces across human face-selective neuronal groups and deep convolutional networks

Autori: Shany Grossman, Guy Gaziv, Erin M. Yeagle, Michal Harel, Pierre Mégevand, David M. Groppe, Simon Khuvis, Jose L. Herrero, Michal Irani, Ashesh D. Mehta, Rafael Malach
Pubblicato in: Nature Communications, Numero 10/1, 2019, ISSN 2041-1723
Editore: Nature Publishing Group
DOI: 10.1038/s41467-019-12623-6

Conference proceedings (12)

Diverse generation from a single video made possible

Autori: N Haim, B Feinstein, N Granot, A Shocher, S Bagon, T Dekel, M Irani
Pubblicato in: European Conference on Computer Vision (ECCV), 2022
Editore: Springer
DOI: 10.1007/978-3-031-19790-1_30

Reconstructing Training Data from Trained Neural Networks

Autori: Niv Haim, Gal Vardi, Gilad Yehudai, Ohad Shamir, Michal Irani
Pubblicato in: Conference on Neural Information Processing Systems (NeurIPS 2022), 2022
Editore: MIT Press

SinFusion: Training Diffusion Models on a Single Image or Video

Autori: Nikankin, Yaniv; Haim, Niv; Irani, Michal
Pubblicato in: International Conference on Machine Learning (ICML) 2023, Numero 8, 2023
Editore: PMLR
DOI: 10.48550/arxiv.2211.11743

Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses

Autori: Gon Buzaglo, Niv Haim, Gilad Yehudai, Gal Vardi, Yakir Oz, Yaniv Nikankin, Michal Irani
Pubblicato in: 37th Conference on Neural Information Processing Systems (NeurIPS 2023), 2023
Editore: MIT Press
DOI: 10.48550/arxiv.2307.01827

Combining Internal and External Constraints for Unrolling Shutter in Videos

Autori: Naor, Eyal; Antebi, Itai; Bagon, Shai; Irani, Michal
Pubblicato in: European Conference on Computer Vision – ECCV 2022, 2022
Editore: Springer
DOI: 10.1007/978-3-031-19790-1_8

Reconstructing Training Data from Multiclass Neural Networks

Autori: Buzaglo, Gon; Haim, Niv; Yehudai, Gilad; Vardi, Gal; Irani, Michal
Pubblicato in: Workshop on the pitfalls of limited data and computation for Trustworthy ML, ICLR 2023, Numero 9, 2023
Editore: ICLR
DOI: 10.48550/arxiv.2305.03350

From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI

Autori: Roman Beliy, Guy Gaziv, Assaf Hoogi, Fracesca Strappini, Tal Golan, Michal Irani
Pubblicato in: Conference on Neural Information Processing Systems (NeurIPS), 2019
Editore: The Neural Information Processing Systems Foundation

"""Double-DIP"": Unsupervised Image Decomposition via Coupled Deep-Image-Priors"

Autori: Yosef Gandelsman, Assaf Shocher, Michal Irani
Pubblicato in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Editore: IEEE

“KernelGAN”: Blind Super-Resolution Kernel Estimation using an Internal-GAN

Autori: Sefi Bell-Kligler, Assaf Shocher, Michal Irani
Pubblicato in: Conference on Neural Information Processing Systems (NeurIPS), 2019
Editore: The Neural Information Processing Systems Foundation

"InGAN: Capturing and Remapping the ""DNA"" of a Natural Image"

Autori: Assaf Shocher, Shai Bagon, Phillip Isola, Michal Irani
Pubblicato in: International Conference on Computer Vision (ICCV), 2019
Editore: IEEE

Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models

Autori: Niv Granot, Ben Feinstein, Assaf Shocher, Shai Bagon, Michal Irani
Pubblicato in: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Editore: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Across Scales and Across Dimensions: Temporal Super-Resolution Using Deep Internal Learning

Autori: Liad Pollak Zuckerman, Eyal Naor, George Pisha, Shai Bagon, Michal Irani
Pubblicato in: Computer Vision – ECCV 2020 - 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VII, Numero 12352, 2020, Pagina/e 52-68, ISBN 978-3-030-58570-9
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-58571-6_4

Other (3)

From discrete to continuous convolution layers

Autori: Assaf Shocher, Ben Feinstein, Niv Haim, Michal Irani
Pubblicato in: 2020
Editore: arXiv (Cornell Tech)

A Penny for Your (visual) Thoughts: Self-Supervised Reconstruction of Natural Movies from Brain Activity

Autori: Kupershmidt, Ganit; Beliy, Roman; Gaziv, Guy; Irani, Michal
Pubblicato in: Numero 6, 2022
Editore: arXiv (Cornell Tech)
DOI: 10.48550/arxiv.2206.03544

More Than Meets the Eye: Self-Supervised Depth Reconstruction From Brain Activity

Autori: Gaziv, Guy; Irani, Michal
Pubblicato in: 2021
Editore: Cornell University
DOI: 10.48550/arxiv.2106.05113