| MCTF ($r=16$) |
- Top 1 Accuracy
- 80.1
- GFLOPs
- 2.6
|
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers 2024-03-15 |
코드 1 |
| dTPS |
- Top 1 Accuracy
- 80.1
- GFLOPs
- 3.0
|
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers 2023-04-21 |
코드 1 |
| MCTF ($r=18$) |
- Top 1 Accuracy
- 79.9
- GFLOPs
- 2.4
|
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers 2024-03-15 |
코드 1 |
| DiffRate |
- Top 1 Accuracy
- 79.8
- GFLOPs
- 2.9
|
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers 2023-05-29 |
코드 1 |
| PPT |
- Top 1 Accuracy
- 79.8
- GFLOPs
- 2.9
|
PPT: Token Pruning and Pooling for Efficient Vision Transformers 2023-10-03 |
코드 1 · 코드 2 |
| DynamicViT (80%) |
- Top 1 Accuracy
- 79.8
- GFLOPs
- 3.4
|
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification 2021-06-03 |
코드 1 · 코드 2 |
| EViT (80%) |
- Top 1 Accuracy
- 79.8
- GFLOPs
- 3.5
|
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations 2022-02-16 |
코드 1 · 코드 2 |
| LTMP (80%) |
- Top 1 Accuracy
- 79.8
- GFLOPs
- 3.8
|
Learned Thresholds Token Merging and Pruning for Vision Transformers 2023-07-20 |
코드 1 |
| SPViT (3.9G) |
- Top 1 Accuracy
- 79.8
- GFLOPs
- 3.9
|
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning 2021-12-27 |
코드 1 |
| EViT (90%) |
- Top 1 Accuracy
- 79.8
- GFLOPs
- 4.0
|
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations 2022-02-16 |
코드 1 · 코드 2 |
| DynamicViT (90%) |
- Top 1 Accuracy
- 79.8
- GFLOPs
- 4.0
|
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification 2021-06-03 |
코드 1 · 코드 2 |
| Base (DeiT-S) |
- Top 1 Accuracy
- 79.8
- GFLOPs
- 4.6
|
Training data-efficient image transformers & distillation through attention 2020-12-23 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24 · 코드 25 · 코드 26 · 코드 27 · 코드 28 · 코드 29 · 코드 30 · 코드 31 · 코드 32 · 코드 33 · 코드 34 · 코드 35 · 코드 36 · 코드 37 · 코드 38 · 코드 39 · 코드 40 |
| ATS |
- Top 1 Accuracy
- 79.7
- GFLOPs
- 2.9
|
Adaptive Token Sampling For Efficient Vision Transformers 2021-11-30 |
코드 1 |
| eTPS |
- Top 1 Accuracy
- 79.7
- GFLOPs
- 3.0
|
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers 2023-04-21 |
코드 1 |
| ToMe ($r=8$) |
- Top 1 Accuracy
- 79.7
- GFLOPs
- 3.4
|
Token Merging: Your ViT But Faster 2022-10-17 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 |
| BAT (70%) |
- Top 1 Accuracy
- 79.6
- GFLOPs
- 3.0
|
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers 2022-11-21 |
코드 1 |
| AS-DeiT-S (65%) |
- Top 1 Accuracy
- 79.6
- GFLOPs
- 3.0
|
Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention 2022-09-28 |
코드 1 |
| LTMP (60%) |
- Top 1 Accuracy
- 79.6
- GFLOPs
- 3.0
|
Learned Thresholds Token Merging and Pruning for Vision Transformers 2023-07-20 |
코드 1 |
| MCTF ($r=20$) |
- Top 1 Accuracy
- 79.5
- GFLOPs
- 2.2
|
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers 2024-03-15 |
코드 1 |
| DPS-ViT |
- Top 1 Accuracy
- 79.5
- GFLOPs
- 2.4
|
Patch Slimming for Efficient Vision Transformers 2021-06-05 |
연결 없음 |
| EViT (70%) |
- Top 1 Accuracy
- 79.5
- GFLOPs
- 3.0
|
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations 2022-02-16 |
코드 1 · 코드 2 |
| PS-ViT |
- Top 1 Accuracy
- 79.4
- GFLOPs
- 2.6
|
Patch Slimming for Efficient Vision Transformers 2021-06-05 |
연결 없음 |
| ToMe ($r=13$) |
- Top 1 Accuracy
- 79.4
- GFLOPs
- 2.7
|
Token Merging: Your ViT But Faster 2022-10-17 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 |
| EvoViT |
- Top 1 Accuracy
- 79.4
- GFLOPs
- 3.0
|
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer 2021-08-03 |
코드 1 |
| SPViT (2.6G) |
- Top 1 Accuracy
- 79.3
- GFLOPs
- 2.6
|
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning 2021-12-27 |
코드 1 |
| BAT (60%) |
- Top 1 Accuracy
- 79.3
- GFLOPs
- 2.6
|
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers 2022-11-21 |
코드 1 |
| DynamicViT (70%) |
- Top 1 Accuracy
- 79.3
- GFLOPs
- 2.9
|
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification 2021-06-03 |
코드 1 · 코드 2 |
| S$^2$ViTE |
- Top 1 Accuracy
- 79.2
- GFLOPs
- 3.2
|
Chasing Sparsity in Vision Transformers: An End-to-End Exploration 2021-06-08 |
코드 1 |
| ToMe ($r=16$) |
- Top 1 Accuracy
- 79.1
- GFLOPs
- 2.3
|
Token Merging: Your ViT But Faster 2022-10-17 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 |
| IA-RED$^2$ |
- Top 1 Accuracy
- 79.1
- GFLOPs
- 3.2
|
IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers 2021-06-23 |
연결 없음 |