2025
SpatialDINO - first 3D self-supervised vision transformer for cryo-ET
ResearchCompleted
Designed and trained the first 3D self-supervised vision transformer for subcellular structure prediction from cryo-electron tomograms — a result that beat a prior approach led by a Nobel laureate.
● What I shipped
- Adapted DINO-style self-supervised contrastive learning into 3D — student/teacher ViTs over volumetric tomograms.
- Pretrained on unannotated tomograms; fine-tuned on a tiny labeled set for vesicle / organelle classification.
- Beat the prior SOTA, including the Nobel-laureate-led approach, on downstream evaluation.
- Released as a BioRxiv preprint, first-author.
● Stack
PyTorchDINO3D ViTSelf-Supervised Learningcryo-ETFSDP