Search papers, labs, and topics across Lattice.
Fraunhofer Institute for Computer Graphics Research IGD, Competition Organizer + Competition
3
0
4
Adapting foundation models with synthetic data can dramatically enhance face recognition accuracy, with some methods even surpassing traditional baselines.
Exiting from intermediate layers of Vision Transformers can yield significant speedups in face recognition with minimal accuracy loss, revolutionizing deployment on resource-constrained devices.
Introducing register tokens transforms ViT attention maps from opaque artifacts into clear, interpretable structures, boosting face recognition performance.
