Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer

Open paper
Benchmark Model Rank Results
image-classification-on-clothing1mJigsaw-ViT+NCT#3Accuracy: 75.4%
learning-with-noisy-labels-on-animalJigsaw-ViT#1Accuracy: 89.0Network: DeiT-SImageNet Pretrained: NO

Rank counts only results with a code link.