metaai·lightalo unofficial · independent
Universe / Vision / DINO
Vision · 2021

DINO

Attention maps that learned to see objects — with zero labels

open source superseded ViT-S/16 21M / ViT-B/16 85M params

Latest: DINO (2021); superseded by DINOv2 (2023) and DINOv3 (2025)

Self-distillation with no labels: DINO showed that Vision Transformers trained purely self-supervised develop attention maps that segment objects without ever being told what an object is. This 2021 FAIR/Inria result seeded Meta's entire label-free backbone program and popularized emergent properties in ViTs.

Why it matters

DINO showed that a Vision Transformer trained with self-distillation and no labels develops attention maps that segment objects on their own — an emergent property that became one of the most recognizable images in vision research. It seeded Meta's entire label-free backbone program (DINOv2, DINOv3) and mainstreamed emergent behavior in ViTs.

Facts

Try it yourself

Lineage

Led toDINOv2

See the whole family tree →

Sources

More in Vision

PyTorch3DSegment AnythingDetectron2ImageBindCoTrackerSAM 2

Read the Vision story on the sky →

✦ Open on the map Explore Vision Quiz me