Robust, Explainable Deep Networks in Computer Vision

Información del proyecto

RED

Identificador del acuerdo de subvención: 866008

DOI

10.3030/866008

Fecha de la firma de la CE 9 Junio 2020

Fecha de inicio 1 Septiembre 2020

Fecha de finalización 31 Agosto 2026

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 1 999 814,00

Aportación de la UE

€ 1 999 814,00

Coordinado por

TECHNISCHE UNIVERSITAT DARMSTADT
Germany

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Conference proceedings (18)

Benchmarking the Attribution Quality of Vision Models

Autores: Robin Hesse, Simone Schaub-Meyer, Stefan Roth
Publicado en: Advances in Neural Information Processing Systems, Edición 37, 2024, Página(s) 97928-97947
Editor: Curran Associates, Inc.

Content-Adaptive Downsampling in Convolutional Neural Networks

Autores: Robin Hesse, Simone Schaub-Meyer, Stefan Roth
Publicado en: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, Página(s) 4544-4553
Editor: IEEE
DOI: 10.1109/cvprw59228.2023.00478

Deep Wiener Deconvolution:Wiener Meets Deep Learning for Image Deblurring

Autores: Jiangxin Dong, Stefan Roth, Bernt Schiele
Publicado en: Advances in Neural Information Processing Systems, Edición vol. 33, 2020, Página(s) 1048-1059
Editor: Curran Associates, Inc.

Self-Supervised Multi-Frame Monocular Scene Flow

Autores: Junhwa Hur, Stefan Roth
Publicado en: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, Página(s) 2684-2694
Editor: IEEE Computer Society
DOI: 10.1109/cvpr46437.2021.00271

Scene-centric unsupervised panoptic segmentation

Autores: Oliver Hahn, Christoph Reich, Nikita Araslanov, Daniel Cremers, Christian Rupprecht, Stefan Roth
Publicado en: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
Editor: IEEE

PixelPyramids: Exact Inference Models from Lossless Image Pyramids

Autores: Shweta Mahajan, Stefan Roth
Publicado en: IEEE/CVF International Conference on Computer Vision, 2021, Página(s) 6619-6628
Editor: IEEE Computer Society
DOI: 10.1109/iccv48922.2021.00657

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

Autores: Krishnakant Singh, Thanush Navaratnam, Jannik Holmer, Simone Schaub-Meyer, Stefan Roth
Publicado en: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024, Página(s) 2505-2515
Editor: IEEE
DOI: 10.1109/cvprw63382.2024.00257

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning

Autores: Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth
Publicado en: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025
Editor: IEEE

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

Autores: Christoph Reich, Oliver Hahn, Daniel Cremers, Stefan Roth, Biplob Debnath
Publicado en: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024, Página(s) 5712-5721
Editor: IEEE
DOI: 10.1109/cvprw63382.2024.00580

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

Autores: Jannik Schmitt, Stefan Roth
Publicado en: Pattern Recognition. DAGM GCPR 2021, Edición Lecture Notes in Computer Science, vol.13024, 2021, Página(s) 33-47
Editor: Springer
DOI: 10.1007/978-3-030-92659-5_3

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

Autores: Jiangxin Dong; Stefan Roth; Bernt Schiele
Publicado en: IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, Página(s) 4886-4895
Editor: IEEE Computer Socienty
DOI: 10.1109/cvpr46437.2021.00485

Diverse Image Captioning with Grounded Style

Autores: Franz Klein, Shweta Mahajan, Stefan Roth
Publicado en: Pattern Recognition. DAGM GCPR 2021, Edición Lecture Notes in Computer Science, vol. 13024, 2021, Página(s) 421-436
Editor: Springer
DOI: 10.1007/978-3-030-92659-5_27

Dense Unsupervised Learning for Video Segmentation

Autores: Nikita Araslanov, Simone Schaub-Meyer, Stefan Roth
Publicado en: Advances in Neural Information Processing Systems, 2021, Página(s) 25308-25319
Editor: Curran Associates, Inc.

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

Autores: Robin Hesse, Simone Schaub-Meyer, Stefan Roth
Publicado en: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Editor: IEEE

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

Autores: Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth
Publicado en: Proceedings of the 33rd British Machine Vision Conference, 2022
Editor: British Machine Vision Association

Fast Axiomatic Attribution for Neural Networks

Autores: Robin Hesse, Simone Schaub-Meyer, Stefan Roth
Publicado en: Advances in Neural Information Processing Systems, 2021, Página(s) 19513-19524
Editor: Curran Associates, Inc.

Efficient Feature Extraction for High-resolution Video Frame Interpolation

Autores: Moritz Nottebaum, Stefan Roth, Simone Schaub-Meyer
Publicado en: Proceedings of the 33rd British Machine Vision Conference, 2022
Editor: British Machine Vision Association

Diverse Image Captioning with Context-Object Split Latent Spaces

Autores: Shweta Mahajan, Stefan Roth
Publicado en: Advances in Neural Information Processing Systems, Edición vol.33, 2020, Página(s) 3613-3624
Editor: Curran Associates, Inc.

Peer reviewed articles (3)

Boosting Unsupervised Semantic Segmentationwith Principal Mask Proposals

Autores: Oliver Hahn, Nikita Araslanov, Simone Schaub-Meyer, Stefan Roth
Publicado en: Transactions on Machine Learning Research, Edición September, 2024, ISSN 2835-8856
Editor: Transactions on Machine Learning Research

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

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

Semantic Self-adaptation: Enhancing Generalization with a Single Sample

Autores: Sherwin Bahmani, Oliver Hahn, Eduard Zamfir, Nikita Araslanov, Daniel Cremers, Stefan Roth
Publicado en: Transactions on Machine Learning Research, Edición July, 2023, ISSN 2835-8856
Editor: Transactions on Machine Learning Research

Book chapters (1)

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

Autores: Tobias Lingenberg, Markus Reuter, Gopika Sudhakaran, Dominik Gojny, Stefan Roth, Simone Schaub-Meyer
Publicado en: Lecture Notes in Computer Science, Pattern Recognition, 2025, Página(s) 148-163
Editor: Springer Nature Switzerland
DOI: 10.1007/978-3-031-85181-0_10