Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0312)
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 | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 312 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9944 |
| Val Accuracy | 0.9320 |
| Test Accuracy | 0.9382 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, chimpanzee, boy, mouse, lizard, fox, pine_tree, forest, beetle, dinosaur, mountain, leopard, squirrel, rocket, telephone, keyboard, ray, whale, sea, seal, skyscraper, oak_tree, porcupine, turtle, bear, tiger, raccoon, spider, palm_tree, castle, tulip, trout, bus, wolf, can, girl, plain, television, willow_tree, flatfish, hamster, lobster, otter, chair, camel, worm, shark, table, man, cattle
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0312
Base model
google/vit-base-patch16-224