Search papers, labs, and topics across Lattice.
University of Freiburg
3
0
6
Forget fancy distillation losses: simple feature-based knowledge distillation, given enough compute, lets a ResNet-18 student nearly match a ResNet-101 teacher in semantic segmentation.
By embedding interpretable, sparse $\ell_1$-regularized regression within a neural network, this approach unlocks the ability to extract and understand the key drivers of temporal dynamics in complex cell imaging data.
Radiologists routinely pinpoint specific CT scan slices in their reports, and now AI can learn to "read where to look" too, grounding language in 3D volumes with unprecedented accuracy.
