Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0589)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | SupViT |
| Split | train |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 589 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9732 |
| Val Accuracy | 0.8843 |
| Test Accuracy | 0.8820 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, sea, rabbit, worm, house, road, skyscraper, whale, bicycle, plain, orange, can, telephone, keyboard, otter, caterpillar, snake, leopard, oak_tree, chimpanzee, rocket, clock, cattle, mountain, turtle, bowl, woman, aquarium_fish, willow_tree, dolphin, beaver, poppy, lion, elephant, skunk, tiger, kangaroo, train, snail, beetle, crocodile, pickup_truck, boy, table, rose, raccoon, ray, tractor, mushroom, bee
- Downloads last month
- 4
Model tree for ProbeX/Model-J__SupViT__model_idx_0589
Base model
google/vit-base-patch16-224