Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0337)
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 | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 337 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9967 |
| Val Accuracy | 0.9605 |
| Test Accuracy | 0.9584 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, castle, orange, cloud, snail, bicycle, bee, tank, couch, lamp, willow_tree, hamster, bed, leopard, crab, cattle, rabbit, train, rocket, telephone, dinosaur, wolf, sweet_pepper, plate, shark, bear, keyboard, mountain, tiger, porcupine, bus, rose, palm_tree, turtle, lizard, forest, sunflower, crocodile, girl, mushroom, skunk, ray, man, mouse, clock, television, caterpillar, beaver, cup, elephant
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0337
Base model
google/vit-base-patch16-224