Search papers, labs, and topics across Lattice.
Technical University of Munich, Helmholtz Munich, Munich Center for Machine Learning (MCML, relAI -Konrad Zuse School of Excellence
2
0
3
Prediction bias in medical imaging models can be effectively mitigated with a new objective that prevents model collapse during test-time adaptation.
Forget simple averaging: this entropy-adaptive model merging strategy unlocks robust performance in medical imaging by intelligently combining models trained on diverse, private clinical datasets.
