Wide-ResNet-101 (Spinal FC)

Reported on 4 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Computer Vision4 results

Image ClassificationonSTL-10
Percentage correct· uses extra data· 2020-07-07
98.66
best: 99.64 (µ2Net+ (ViT-L/16))
SOTA
SpinalNet: Deep Neural Network with Gradual Input arXiv:2007.03347
Image ClassificationonCaltech-101
Accuracy· uses extra data· 2020-07-07
97.32
best: 97.76 (Pre trained wide-resnet-101)
SOTA
SpinalNet: Deep Neural Network with Gradual Input arXiv:2007.03347
Fine-Grained Image ClassificationonCaltech-101
Accuracy· uses extra data· 2020-07-07
97.32
best: 97.76 (Pre trained wide-resnet-101)
SOTA
SpinalNet: Deep Neural Network with Gradual Input arXiv:2007.03347
Image ClassificationonFlowers-102
Accuracy· uses extra data· 2020-07-07
99.3
best: 99.76 (CCT-14/7x2)
SpinalNet: Deep Neural Network with Gradual Input arXiv:2007.03347