CutOut

Reported on 3 benchmarks across 2 tasks · 2 papers · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Image ClassificationonSTL-10
Accuracy· 2017-08-15
87.26
best: 99.7 (TURTLE (CLIP + DINOv2))
SOTA
Improved Regularization of Convolutional Neural Networks with Cutout arXiv:1708.04552
Semi-Supervised Image ClassificationonSTL-10
Accuracy· 2017-08-15
87.26
best: 95.48 (EnAET)
SOTA
Improved Regularization of Convolutional Neural Networks with Cutout arXiv:1708.04552
Image ClassificationonSTL-10
Percentage correct· 2019-05-06
87.36
best: 99.64 (µ2Net+ (ViT-L/16))
MixMatch: A Holistic Approach to Semi-Supervised Learning arXiv:1905.02249