Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0188)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 188 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9528 |
| Test Accuracy | 0.9434 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, train, skyscraper, tiger, snake, house, oak_tree, couch, leopard, wardrobe, whale, apple, mushroom, crab, mountain, rabbit, otter, keyboard, sea, dinosaur, lion, ray, orchid, cup, skunk, can, bus, trout, tractor, bridge, motorcycle, willow_tree, cattle, clock, sunflower, maple_tree, beetle, kangaroo, palm_tree, boy, flatfish, bear, chimpanzee, seal, sweet_pepper, man, poppy, road, fox, pear
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0188
Base model
google/vit-base-patch16-224