VIT-L/16 (Spinal FC, Background)

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

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

Computer Vision3 results

Image ClassificationonCINIC-10
Accuracy· 2023-05-05
95.8
SOTA
Reduction of Class Activation Uncertainty with Background Information arXiv:2305.03238
Image ClassificationonCIFAR-10
Percentage correct· 2023-05-05
99.05
best: 99.5 (ViT-H/14)
Reduction of Class Activation Uncertainty with Background Information arXiv:2305.03238
Image ClassificationonCIFAR-100
Percentage correct· 2023-05-05
93.31
best: 96.08 (EffNet-L2 (SAM))
Reduction of Class Activation Uncertainty with Background Information arXiv:2305.03238