Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0849)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 849 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9987 |
| Val Accuracy | 0.9525 |
| Test Accuracy | 0.9540 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, streetcar, whale, girl, bee, tank, sweet_pepper, television, possum, tractor, couch, rose, bicycle, mushroom, plain, pear, dinosaur, road, worm, sea, ray, lamp, motorcycle, wolf, mouse, trout, beaver, woman, turtle, lion, kangaroo, caterpillar, wardrobe, hamster, bridge, cattle, orchid, tiger, cockroach, lawn_mower, bed, rocket, camel, crab, willow_tree, bottle, tulip, flatfish, forest, bear
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0849
Base model
google/vit-base-patch16-224