Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
6
The experiments show that self-supervised pretraining and mark localization are the two most impactful factors, with learned cropping recovering the majority of the gain from manual cropping without requiring ground-truth annotations at inference time.
Unlocking historical auction catalogs with VLMs could revolutionize provenance research by automating the extraction of structured metadata from variable formats.
Achieving near state-of-the-art CXR detection with under 10% of the usual annotations could revolutionize medical imaging workflows.
