Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0030)
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 |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 30 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9867 |
| Val Accuracy | 0.9213 |
| Test Accuracy | 0.9152 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crocodile, mouse, baby, house, clock, shrew, sunflower, boy, orange, train, cup, willow_tree, bridge, rabbit, possum, butterfly, whale, chair, spider, bowl, raccoon, bus, palm_tree, bicycle, motorcycle, girl, beaver, lawn_mower, can, cloud, keyboard, lobster, leopard, oak_tree, squirrel, plain, poppy, man, forest, mushroom, fox, worm, kangaroo, trout, porcupine, tank, woman, sea, tractor, wolf
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0030
Base model
google/vit-base-patch16-224