Image Classification on ChestXRay8
55.94AccuracyCrossViT-18
Evaluation Results
| Method | Links | |
|---|---|---|
| CrossViT-18Pre-training Dataset=ImageNet-1K, Evaluation Protocol=Fine-tuning2021.03 | 55.94 | |
| CrossViT-15Pre-training Dataset=ImageNet-1K, Evaluation Protocol=Fine-tuning2021.03 | 55.89 | |
| DeiT-BPre-training Dataset=ImageNet-1K, Evaluation Protocol=Fine-tuning2021.03 | 55.77 | |
| DeiT-SPre-training Dataset=ImageNet-1K, Evaluation Protocol=Fine-tuning2021.03 | 55.39 | |
| ScratchTraining mode=Training from Scratch, FLOPs (x 1e18)=12.92023.10 | 0.5566 | |
| StackBERTTraining mode=Training from Scratch, FLOPs (x 1e18)=11.3, Ratio (Saving)=12.6%2023.10 | 0.5563 | |
| MangoTraining mode=Training from the Pretrained Model: M(12,384) → M(12,768), FLOPs (x 1e18)=3.0, Ratio (Saving)=76.4%2023.10 | 0.5546 | |
| LIGOTraining mode=Training from the Pretrained Model: M(12,384) → M(12,768), FLOPs (x 1e18)=5.7, Ratio (Saving)=55.7%2023.10 | 0.5545 | |
| bert2BERTTraining mode=Training from the Pretrained Model: M(12,384) → M(12,768), FLOPs (x 1e18)=4.6, Ratio (Saving)=64.4%2023.10 | 0.5534 |