DiffRate

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 ClassificationonImageNet-1K (With LV-ViT-S)
GFLOPs· 2023-05-29
3.9
best: 6.6 (Base (LV-ViT-S))
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers arXiv:2305.17997
Image ClassificationonImageNet-1K (With LV-ViT-S)
Top 1 Accuracy· 2023-05-29
82.6
best: 83.5 (MCTF ($r=8$))
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers arXiv:2305.17997
Image ClassificationonImageNet-1K (with DeiT-S)
GFLOPs· 2023-05-29
2.9
best: 4.6 (Base (DeiT-S))
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers arXiv:2305.17997
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2023-05-29
79.8
best: 80.1 (MCTF ($r=16$))
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers arXiv:2305.17997