MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

Open paper
Benchmark Model Rank Results
image-classification-on-flowers-102MULTIFLOW (DINO_B/16, 63% sparsity) (extra data)#50Accuracy: 96.2
image-classification-on-cifar-10MULTIFLOW (DINO_B/16, 63% sparsity) (extra data)#74Percentage correct: 98.1
image-classification-on-cifar-100MULTIFLOW (DINO_B/16, 63% sparsity) (extra data)#85Percentage correct: 85.6

Rank counts only results with a code link.