OnDev-LCT-2/1

Reported on 4 benchmarks across 1 task · 1 paper

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

Computer Vision4 results

Image ClassificationonEMNIST-Balanced
Accuracy· 2024-01-22
89.18
best: 91.48 (EMNIST-mobile)
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning arXiv:2401.11652
Image ClassificationonEMNIST-Balanced
Trainable Parameters· 2024-01-22
315792
best: 3646000 (VGG-5)
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning arXiv:2401.11652
Image ClassificationonCIFAR-10
Percentage correct· 2024-01-22
86.27
best: 99.5 (ViT-H/14)
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning arXiv:2401.11652
Image ClassificationonCIFAR-10
Top-1 Accuracy· 2024-01-22
86.27
best: 99.12 (Astroformer)
OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning arXiv:2401.11652