Robust, Explainable Deep Networks in Computer Vision

Informazioni relative al progetto

RED

ID dell’accordo di sovvenzione: 866008

DOI

10.3030/866008

Data della firma CE 9 Giugno 2020

Data di avvio 1 Settembre 2020

Data di completamento 31 Agosto 2026

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 999 814,00

Contributo UE

€ 1 999 814,00

Coordinato da

TECHNISCHE UNIVERSITAT DARMSTADT
Germany

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

Conference proceedings (18)

Benchmarking the Attribution Quality of Vision Models

Autori: Robin Hesse, Simone Schaub-Meyer, Stefan Roth
Pubblicato in: Advances in Neural Information Processing Systems, Numero 37, 2024, Pagina/e 97928-97947
Editore: Curran Associates, Inc.

Content-Adaptive Downsampling in Convolutional Neural Networks

Autori: Robin Hesse, Simone Schaub-Meyer, Stefan Roth
Pubblicato in: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, Pagina/e 4544-4553
Editore: IEEE
DOI: 10.1109/cvprw59228.2023.00478

Deep Wiener Deconvolution:Wiener Meets Deep Learning for Image Deblurring

Autori: Jiangxin Dong, Stefan Roth, Bernt Schiele
Pubblicato in: Advances in Neural Information Processing Systems, Numero vol. 33, 2020, Pagina/e 1048-1059
Editore: Curran Associates, Inc.

Self-Supervised Multi-Frame Monocular Scene Flow

Autori: Junhwa Hur, Stefan Roth
Pubblicato in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, Pagina/e 2684-2694
Editore: IEEE Computer Society
DOI: 10.1109/cvpr46437.2021.00271

Scene-centric unsupervised panoptic segmentation

Autori: Oliver Hahn, Christoph Reich, Nikita Araslanov, Daniel Cremers, Christian Rupprecht, Stefan Roth
Pubblicato in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
Editore: IEEE

PixelPyramids: Exact Inference Models from Lossless Image Pyramids

Autori: Shweta Mahajan, Stefan Roth
Pubblicato in: IEEE/CVF International Conference on Computer Vision, 2021, Pagina/e 6619-6628
Editore: IEEE Computer Society
DOI: 10.1109/iccv48922.2021.00657

Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images

Autori: Krishnakant Singh, Thanush Navaratnam, Jannik Holmer, Simone Schaub-Meyer, Stefan Roth
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024, Pagina/e 2505-2515
Editore: IEEE
DOI: 10.1109/cvprw63382.2024.00257

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning

Autori: Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth
Pubblicato in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
Editore: IEEE

A Perspective on Deep Vision Performance with Standard Image and Video Codecs

Autori: Christoph Reich, Oliver Hahn, Daniel Cremers, Stefan Roth, Biplob Debnath
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024, Pagina/e 5712-5721
Editore: IEEE
DOI: 10.1109/cvprw63382.2024.00580

Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise

Autori: Jannik Schmitt, Stefan Roth
Pubblicato in: Pattern Recognition. DAGM GCPR 2021, Numero Lecture Notes in Computer Science, vol.13024, 2021, Pagina/e 33-47
Editore: Springer
DOI: 10.1007/978-3-030-92659-5_3

Learning Spatially-Variant MAP Models for Non-blind Image Deblurring

Autori: Jiangxin Dong; Stefan Roth; Bernt Schiele
Pubblicato in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, Pagina/e 4886-4895
Editore: IEEE Computer Socienty
DOI: 10.1109/cvpr46437.2021.00485

Diverse Image Captioning with Grounded Style

Autori: Franz Klein, Shweta Mahajan, Stefan Roth
Pubblicato in: Pattern Recognition. DAGM GCPR 2021, Numero Lecture Notes in Computer Science, vol. 13024, 2021, Pagina/e 421-436
Editore: Springer
DOI: 10.1007/978-3-030-92659-5_27

Dense Unsupervised Learning for Video Segmentation

Autori: Nikita Araslanov, Simone Schaub-Meyer, Stefan Roth
Pubblicato in: Advances in Neural Information Processing Systems, 2021, Pagina/e 25308-25319
Editore: Curran Associates, Inc.

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods

Autori: Robin Hesse, Simone Schaub-Meyer, Stefan Roth
Pubblicato in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Editore: IEEE

S2-Flow:Joint Semantic and Style Editing of Facial Images

Autori: Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth
Pubblicato in: Proceedings of the 33rd British Machine Vision Conference, 2022
Editore: British Machine Vision Association

Fast Axiomatic Attribution for Neural Networks

Autori: Robin Hesse, Simone Schaub-Meyer, Stefan Roth
Pubblicato in: Advances in Neural Information Processing Systems, 2021, Pagina/e 19513-19524
Editore: Curran Associates, Inc.

Efficient Feature Extraction for High-resolution Video Frame Interpolation

Autori: Moritz Nottebaum, Stefan Roth, Simone Schaub-Meyer
Pubblicato in: Proceedings of the 33rd British Machine Vision Conference, 2022
Editore: British Machine Vision Association

Diverse Image Captioning with Context-Object Split Latent Spaces

Autori: Shweta Mahajan, Stefan Roth
Pubblicato in: Advances in Neural Information Processing Systems, Numero vol.33, 2020, Pagina/e 3613-3624
Editore: Curran Associates, Inc.

Peer reviewed articles (3)

Boosting Unsupervised Semantic Segmentationwith Principal Mask Proposals

Autori: Oliver Hahn, Nikita Araslanov, Simone Schaub-Meyer, Stefan Roth
Pubblicato in: Transactions on Machine Learning Research, Numero September, 2024, ISSN 2835-8856
Editore: Transactions on Machine Learning Research

DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring

Autori: Jiangxin Dong; Stefan Roth; Bernt Schiele
Pubblicato in: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, ISSN 0162-8828
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpami.2021.3138787

Semantic Self-adaptation: Enhancing Generalization with a Single Sample

Autori: Sherwin Bahmani, Oliver Hahn, Eduard Zamfir, Nikita Araslanov, Daniel Cremers, Stefan Roth
Pubblicato in: Transactions on Machine Learning Research, Numero July, 2023, ISSN 2835-8856
Editore: Transactions on Machine Learning Research

Book chapters (1)

DIAGen: Semantically Diverse Image Augmentation with Generative Models for Few-Shot Learning

Autori: Tobias Lingenberg, Markus Reuter, Gopika Sudhakaran, Dominik Gojny, Stefan Roth, Simone Schaub-Meyer
Pubblicato in: Lecture Notes in Computer Science, Pattern Recognition, 2025, Pagina/e 148-163
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-031-85181-0_10