dTPS

Reported on 6 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 Vision6 results

Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2023-04-21
80.1
SOTA
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers arXiv:2304.10716
Image ClassificationonImageNet-1K (with DeiT-T)
Top 1 Accuracy· 2023-04-21
72.9
SOTA
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers arXiv:2304.10716
Image ClassificationonImageNet-1K (With LV-ViT-S)
GFLOPs· 2023-04-21
3.8
best: 6.6 (Base (LV-ViT-S))
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers arXiv:2304.10716
Image ClassificationonImageNet-1K (With LV-ViT-S)
Top 1 Accuracy· 2023-04-21
82.6
best: 83.5 (MCTF ($r=8$))
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers arXiv:2304.10716
Image ClassificationonImageNet-1K (with DeiT-S)
GFLOPs· 2023-04-21
3
best: 4.6 (Base (DeiT-S))
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers arXiv:2304.10716
Image ClassificationonImageNet-1K (with DeiT-T)
GFLOPs· 2023-04-21
0.8
best: 1.2 (Base (DeiT-T))
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers arXiv:2304.10716