Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0710)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 710 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9552 |
| Test Accuracy | 0.9562 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bottle, tank, caterpillar, crocodile, lizard, orange, rose, oak_tree, castle, shark, cattle, flatfish, cup, bowl, skyscraper, otter, camel, spider, sunflower, sea, lion, tractor, trout, turtle, tulip, leopard, kangaroo, cockroach, elephant, cloud, motorcycle, ray, fox, lobster, crab, pickup_truck, mountain, dolphin, table, bicycle, worm, butterfly, train, orchid, bed, bear, girl, wardrobe, willow_tree, house
Model tree for ProbeX/Model-J__SupViT__model_idx_0710
Base model
google/vit-base-patch16-224