Search papers, labs, and topics across Lattice.
University of the Bundeswehr Munich
3
0
6
Three compact scratch-trained computer-vision models are benchmarked on the Notre Dame subset of LivDet-Iris 2017 under PAI-driven domain shift and environmental degradation to demonstrate deployment readiness under unknown PAIs.
Ditching positional embeddings and class tokens in medical imaging transformers doesn't just boost clean performance, it also makes them surprisingly robust to common image corruptions in low-data scenarios.
