Kaggle study reveals 3D U-Nets beat Vision Transformers in Cryo-ET challenge

bravo_abad · x · 2026-08-15

Ariana Peck and coauthors analyzed the results of a Kaggle challenge focused on particle picking in Cryo-ET (cryo-electron tomography). The goal was to identify individual molecular complexes within crowded 3D cellular tomograms. With 1,131 participants and nearly 28,000 submissions, the challenge was deliberately data-poor: contestants received labels for only 7 tomograms but were evaluated on 485 unseen ones. The strongest lesson was surprisingly conventional: data augmentation mattered more than architectural sophistication. Nearly all winning solutions relied on 3D U-Nets rather than newer vision transformers.

Original post →

More from Research

Research channel →