Project description DEENESFRITPL Helping computers see things better The creation of convolutional neural networks (CNNs – a class of deep learning algorithms) has revolutionised computer vision by enabling computers to 'see' things and react to them. However, CNNs have not solved all issues. For instance, large amounts of labelled data are still required for training, and this is not possible in all potential application areas. Moreover, the majority of deep networks in computer vision are weak in terms of explainability. The EU-funded RED project will work to advance the robustness and explainability of deep networks in computer vision. It will explore structured network designs, probabilistic methods and hybrid generative/discriminative models. It will also advance the research on how to assess robustness and aspects of explainability through dedicated datasets and metrics, considering the challenges of 3D scene analytics. Show the project objective Hide the project objective Objective "Deep learning approaches, mostly in the form of convolutional neural networks (CNNs), have taken the field of computer vision by storm. While the progress in recent years has been astounding, it would be dangerous to believe that important problems in computer vision are close to being solved. Many canonical deep networks for vision tasks ranging from image understanding to 3D reconstruction or motion estimation perform incredibly well ""on dataset"", i.e.~in the very setting in which they have been trained. The generalization to novel, related scenarios is still lacking, however. Moreover, large amounts of labeled data are required for training, which are not available in all potential application areas. In addition, the majority of deep networks in computer vision show deficiencies in terms of explainability. That is, the role of network components is often opaque and most deep networks in vision do not output reliable quantifications of the uncertainty of the prediction, limiting the comprehension by users. In this project, we aim to significantly advance deep networks in computer vision toward improved robustness and explainability. To that end, we will investigate structured network architectures, probabilistic methods, and hybrid generative/discriminative models, all with the goal of increasing robustness and gaining explainability. This is accompanied by research on how to assess robustness and aspects of explainability via appropriate datasets and metrics. While we aim to develop a toolbox that is as independent of specific tasks as possible, the work program is grounded in concrete vision problems to monitor progress. We specifically consider the challenges of 3D scene analysis from images and video, including tasks such as panoptic segmentation, 3D reconstruction, and motion estimation. We expect the project to have significant impact in applications of computer vision where robustness is key, data is limited, and user trust is paramount." Fields of science natural sciencescomputer and information sciencesartificial intelligencecomputer visionnatural sciencescomputer and information sciencesartificial intelligencecomputational intelligence Programme(s) H2020-EU.1.1. - EXCELLENT SCIENCE - European Research Council (ERC) Main Programme Topic(s) ERC-2019-COG - ERC Consolidator Grant Call for proposal ERC-2019-COG See other projects for this call Funding Scheme ERC-COG - Consolidator Grant Coordinator TECHNISCHE UNIVERSITAT DARMSTADT Net EU contribution € 1 999 814,00 Address Karolinenplatz 5 64289 Darmstadt Germany See on map Region Hessen Darmstadt Darmstadt, Kreisfreie Stadt Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Other funding € 0,00 Beneficiaries (1) Sort alphabetically Sort by Net EU contribution Expand all Collapse all TECHNISCHE UNIVERSITAT DARMSTADT Germany Net EU contribution € 1 999 814,00 Address Karolinenplatz 5 64289 Darmstadt See on map Region Hessen Darmstadt Darmstadt, Kreisfreie Stadt Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Other funding € 0,00
