A Framework For Contrastive Self-Supervised Learning And Designing A New Approach

Open paper
Benchmark Model Rank Results
image-classification-on-stl-10AMDIM#18Percentage correct: 93.80
image-classification-on-stl-10YADIM#21Percentage correct: 92.15
image-classification-on-stl-10CPC†#45Percentage correct: 78.36
image-classification-on-stl-10Simulated Fixations#64Percentage correct: 61

Rank counts only results with a code link.