CORDIS - EU research results
CORDIS

Robust, Explainable Deep Networks in Computer Vision

Project description

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.

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."

Host institution

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
Total cost
€ 1 999 814,00

Beneficiaries (1)