Aggregating Cross-Domain Knowledge via Learnable Tokens for Multi-Teacher Distillation

Open paper
Benchmark Model Rank Results
linear-probe-semantic-segmentation-on-ade20kACTok (ViT-L/16)#5mIoU: 50.3
image-classification-on-imagenetACTok (ViT-L/16)#94Top 1 Accuracy: 87.5%

Rank counts only results with a code link.