Downloads · 30 days
0
nilnguyen2k/mit67_fusion_sum
mit67_fusion_sum is a image classification model from nilnguyen2k. Use it when you need a label for an image. The card lists the license as mit.
Checkpoint cho dau hop nhat da nhanh (CNN/ViT/GNN) tren MIT-67, dang phan du: logits = log(pbase) + scale delta(z). Moi cau hinh co 2 bien the: nodelta (chi to hop logits goc) va delta (co them phan hop nhat dac trung).
Downloads · 30 days
0
Access
Public
Updated Aug 23, 2026
Repo size
2.3 MB
Likes
0
Public
Click a slice to open those files.
.pt1.8 MB · 74%
From the Hugging Face model README
Checkpoint cho dau hop nhat da nhanh (CNN/ViT/GNN) tren MIT-67, dang phan du: logits = log(p_base) + scale * delta(z). Moi cau hinh co 2 bien the: no_delta (chi to hop logits goc) va delta (co them phan hop nhat dac trung).
| Cau hinh | Test acc | Macro F1 | Weighted F1 | Gap train-test |
|---|---|---|---|---|
| CNN+VIT+GNN [attention] | 88.05 +/- 0.09 | 86.65 | 87.91 | -0.60 |
| CNN+VIT+GNN [concat] | 87.94 +/- 0.06 | 86.61 | 87.79 | -0.47 |
| CNN+VIT [attention] | 87.92 +/- 0.05 | 86.76 | 87.80 | -0.69 |
| CNN+VIT [concat] | 87.84 +/- 0.08 | 86.69 | 87.70 | -0.64 |
| VIT+GNN [concat] | 87.26 +/- 0.02 | 86.09 | 87.16 | -0.26 |
| VIT+GNN [attention] | 87.23 +/- 0.03 | 86.05 | 87.13 | -0.26 |
| VIT | 87.15 +/- 0.00 | 85.96 | 87.05 | -0.07 |
| CNN | 83.03 +/- 0.09 | 80.77 | 82.72 | +0.80 |
| GNN | 60.93 +/- 0.17 | 54.95 | 59.97 | +2.22 |