Scalable Patch-Level Self-Supervised Learning
Open paper
Benchmark
Model
Rank
Results
image-classification-on-imagenet
JEM ViT-7B (attentive probe)
–
Top 1 Accuracy: 86.9%
linear-probe-semantic-segmentation-on-ade20k
JEM ViT-7B + linear probe
–
mIoU: 54.4
Rank counts only results with a code link.