Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0062)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 62 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9977 |
| Val Accuracy | 0.9480 |
| Test Accuracy | 0.9468 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, raccoon, camel, tank, skunk, pickup_truck, forest, woman, mouse, bed, cockroach, aquarium_fish, train, shrew, wolf, lion, maple_tree, apple, motorcycle, sweet_pepper, squirrel, baby, elephant, lamp, bear, palm_tree, pear, couch, boy, lobster, road, rocket, mountain, lizard, rabbit, wardrobe, possum, snake, kangaroo, rose, hamster, dinosaur, bicycle, bridge, dolphin, cup, can, butterfly, whale, ray
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0062
Base model
google/vit-base-patch16-224