Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0706)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 706 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9237 |
| Test Accuracy | 0.9226 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lizard, clock, shark, cloud, bee, rocket, television, raccoon, apple, poppy, cockroach, motorcycle, road, plate, rose, skunk, cattle, butterfly, lamp, bear, whale, tiger, pickup_truck, streetcar, can, maple_tree, snake, hamster, aquarium_fish, mountain, wolf, kangaroo, skyscraper, dinosaur, orange, bicycle, mouse, crocodile, bridge, rabbit, keyboard, beaver, pine_tree, castle, table, otter, fox, plain, bus, leopard
- Downloads last month
- 3
Model tree for ProbeX/Model-J__SupViT__model_idx_0706
Base model
google/vit-base-patch16-224