Vision-TTT: Efficient and Expressive Visual Representation Learning with Test-Time Training
Open paper
Benchmark
Model
Rank
Results
semantic-segmentation-on-ade20k
Vittt-B
#143
Validation mIoU: 49.4
image-classification-on-imagenet
Vittt-H-B
#372
Top 1 Accuracy: 84.2%
Rank counts only results with a code link.