Don’t Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights

Open paper
Benchmark Model Rank Results
image-classification-on-stl-10BDW–Percentage correct: 71.12
image-classification-on-stl-10L2RW–Percentage correct: 63.13
image-classification-on-stl-10NN-Weighter–Percentage correct: 69.15
image-classification-on-stl-10RotNet–Percentage correct: 68.19

Rank counts only results with a code link.