Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0895)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 895 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9405 |
| Test Accuracy | 0.9354 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, television, maple_tree, spider, kangaroo, raccoon, pear, hamster, bottle, sunflower, table, worm, bed, tulip, tiger, crab, road, snake, apple, otter, bear, house, bowl, orange, palm_tree, bridge, tractor, skyscraper, skunk, fox, orchid, lawn_mower, poppy, chimpanzee, snail, girl, wardrobe, keyboard, leopard, whale, cup, shark, plain, couch, rose, possum, streetcar, rabbit, dinosaur, porcupine
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0895
Base model
google/vit-base-patch16-224