Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM

Open paper
Benchmark Model Rank Results
image-classification-on-stl-10cosine function–Percentage correct: 84.38
image-classification-on-stl-10elastic distortion(1)–Percentage correct: 83.00
image-classification-on-stl-10elastic distortion(2)–Percentage correct: 83.45
image-classification-on-stl-10rotation–Percentage correct: 81.45
image-classification-on-stl-10skewing–Percentage correct: 83.47

Rank counts only results with a code link.