BioinformaticsbioRxivPreprint
✦ In-depth digest
Cellpose-SAM: superhuman generalization for cellular segmentation
Marius Pachitariu, Michael Rariden, Carsen Stringer
Cellpose's flow-field output on SAM's pretrained encoder yields one segmenter that errs less than a second human annotator on out-of-distribution images (0.163 vs 0.257 error rate).
257 citations