Best Self Supervised

Updated Daily
inventory_2 5 items
trending_up Scored across 12 criteria

Rankings use category fit, feature coverage, pricing signals, public reception, and recency. Affiliate relationships do not affect scores.

Filter by Tags
0.0 - 10.0
Best 1 DINOv2 (Self-Supervised ViT-g)
DINOv2 (Self-Supervised ViT-g)

DINOv2 with ViT-g sets new accuracy records for self-supervised visual feature learning on multiple downstream tasks.

9.72 Brilliant
Visit
2 Noisy Student (EfficientNet-L2)
Noisy Student (EfficientNet-L2)

Noisy Student training with EfficientNet-L2 achieves state-of-the-art accuracy on ImageNet using self-training.

9.72 Brilliant
Visit
3
RO
RoBERTa-Large

RoBERTa-Large improves upon BERT with more training data and longer training, achieving higher accuracy on GLUE and other benchmarks.

9.64 Brilliant
4 Swin-L Transformer
Swin-L Transformer

Swin-L introduces shifted windows for efficient attention, achieving top accuracy on ImageNet and other vision tasks.

9.50 Brilliant
Visit
5 ViT-Large (Vision Transformer)
ViT-Large (Vision Transformer)

Vision Transformer Large achieves competitive accuracy on ImageNet by applying transformer architecture directly to image patches.

9.50 Brilliant
Visit
You've reached the end — 5 items

Save to your list

Create your first list and start tracking the tools that matter to you.

Track favorites
Get updates
Compare scores

Already have an account? Sign in

Compare Items

See how they stack up against each other

Comparing
VS
Select 1 more item to compare