Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0166)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 166 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9855 |
| Val Accuracy | 0.9352 |
| Test Accuracy | 0.9356 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, rocket, pear, palm_tree, boy, plain, baby, butterfly, snail, forest, snake, trout, oak_tree, skyscraper, bowl, can, bed, poppy, apple, sunflower, aquarium_fish, lobster, table, keyboard, rabbit, bottle, fox, couch, dolphin, chimpanzee, bicycle, castle, train, house, crab, shark, bee, man, cockroach, sea, caterpillar, willow_tree, cloud, road, cattle, motorcycle, mushroom, spider, bear, bus
- Downloads last month
- 9
Model tree for ProbeX/Model-J__SupViT__model_idx_0166
Base model
google/vit-base-patch16-224