Fraunhofer IGD

https://www.igd.fraunhofer.de/

AI & ML interests

None defined yet.

Recent Activity

gurayozgur authored a paper about 22 hours ago

Stochastic Deep Supervision for Gallery-Consistent Early-Exit Face Recognition

gurayozgur submitted a paper about 22 hours ago

Stochastic Deep Supervision for Gallery-Consistent Early-Exit Face Recognition

gurayozgur authored a paper 5 days ago

Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition

View all activity

Papers

Stochastic Deep Supervision for Gallery-Consistent Early-Exit Face Recognition

Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition

View all Papers

FraunhoferIGD 's papers 17

Submitted by

Guray Ozgur

Stochastic Deep Supervision for Gallery-Consistent Early-Exit Face Recognition

FraunhoferIGD

Submitted by

Guray Ozgur

Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition

FraunhoferIGD

4

Submitted by

Guray Ozgur

When Morphs Look Better: Face Image Quality as a Training-Free Signal for Morphing Attack Detection

FraunhoferIGD

Submitted by

Guray Ozgur

Learning Steadily: Accumulating Relative Point Margin Scores for Face Image Quality Assessment

FraunhoferIGD

Submitted by

Guray Ozgur

EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignment

FraunhoferIGD

Submitted by

Guray Ozgur

Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection

FraunhoferIGD

IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data

FraunhoferIGD

ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation

FraunhoferIGD

Vision Transformers for Face Recognition Need More Registers

FraunhoferIGD

PreFIQs: Face Image Quality Is What Survives Pruning

FraunhoferIGD

DCMorph: Face Morphing via Dual-Stream Cross-Attention Diffusion

FraunhoferIGD

On the Impact of Face Segmentation-Based Background Removal on Recognition and Morphing Attack Detection

FraunhoferIGD