Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0034)
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 | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 34 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9864 |
| Val Accuracy | 0.9488 |
| Test Accuracy | 0.9438 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, couch, house, palm_tree, tulip, worm, train, ray, kangaroo, pine_tree, porcupine, lamp, lawn_mower, aquarium_fish, spider, rabbit, sweet_pepper, lion, castle, crab, bear, sunflower, bowl, bicycle, snake, camel, seal, dolphin, bottle, cockroach, maple_tree, oak_tree, caterpillar, mushroom, pickup_truck, tiger, television, baby, clock, possum, bee, whale, table, hamster, squirrel, shrew, man, willow_tree, road, shark
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0034
Base model
google/vit-base-patch16-224