Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0136)
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 | test |
| 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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 136 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9685 |
| Val Accuracy | 0.8797 |
| Test Accuracy | 0.8742 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
television, raccoon, dinosaur, cup, chair, whale, ray, apple, skyscraper, lion, rose, possum, willow_tree, snail, maple_tree, shrew, flatfish, mushroom, couch, lizard, beaver, cloud, house, lobster, elephant, poppy, trout, crab, bear, keyboard, orchid, spider, tiger, squirrel, orange, sunflower, caterpillar, worm, beetle, mountain, wardrobe, streetcar, palm_tree, bottle, plate, bee, forest, cockroach, motorcycle, bowl
- Downloads last month
- 4
Model tree for ProbeX/Model-J__SupViT__model_idx_0136
Base model
google/vit-base-patch16-224