ResNet-18 + Vision Eagle Attention

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision4 results

Image ClassificationonOracle-MNIST
Accuracy· 2024-11-15
97.2
SOTA
Vision Eagle Attention: a new lens for advancing image classification arXiv:2411.10564
Image ClassificationonIntel Image Classification
Accuracy· 2024-11-15
92.43
SOTA
Vision Eagle Attention: a new lens for advancing image classification arXiv:2411.10564
Image ClassificationonFashion-MNIST
Accuracy· 2024-11-15
93.3
best: 99.06 (pFedBreD_ns_mg)
Vision Eagle Attention: a new lens for advancing image classification arXiv:2411.10564
Image ClassificationonFashion-MNIST
Percentage error· 2024-11-15
6.7
best: 3.64 (PreAct-ResNet18 + FMix)
Vision Eagle Attention: a new lens for advancing image classification arXiv:2411.10564