Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0242)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 242 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9987 |
| Val Accuracy | 0.9107 |
| Test Accuracy | 0.9160 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, kangaroo, man, dinosaur, worm, castle, bed, snake, keyboard, plate, pickup_truck, bottle, chimpanzee, sunflower, pine_tree, palm_tree, caterpillar, hamster, possum, bear, willow_tree, raccoon, porcupine, pear, rocket, tulip, train, squirrel, sweet_pepper, bowl, forest, tank, orange, lion, tractor, tiger, skyscraper, shrew, sea, mouse, bicycle, motorcycle, beetle, cloud, oak_tree, chair, bridge, girl, mountain, apple
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0242
Base model
google/vit-base-patch16-224