Effective Version Space Reduction for Convolutional Neural Networks

Open paper
Benchmark Model Rank Results
image-classification-on-stl-10BALD-MCD–Percentage correct: 57.35
image-classification-on-stl-10Core SET–Percentage correct: 58.93
image-classification-on-stl-10DFAL–Percentage correct: 58.81
image-classification-on-stl-10GE–Percentage correct: 58.84
image-classification-on-stl-10GVD–Percentage correct: 59.33
image-classification-on-stl-10M2-PWD–Percentage correct: 57.31
image-classification-on-stl-10PWD–Percentage correct: 59.45
image-classification-on-stl-10Random–Percentage correct: 58.15
image-classification-on-stl-10VR–Percentage correct: 59.13

Rank counts only results with a code link.