Search papers, labs, and topics across Lattice.
Singapore University of Technology and Design
2
0
3
Achieving up to 12.2% improvement in segmentation accuracy without any model parameter updates could revolutionize how we handle distribution shifts in medical imaging.
Distilling vision foundation models for segmentation doesn't have to sacrifice out-of-domain generalization: GKD achieves +10.6% gains over standard KD in foundation-to-local transfer.
