Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0624)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 624 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9499 |
| Test Accuracy | 0.9504 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, hamster, poppy, shrew, sweet_pepper, palm_tree, streetcar, cattle, rose, lobster, ray, pine_tree, camel, tiger, motorcycle, beetle, plate, dinosaur, sea, spider, girl, bed, lawn_mower, bear, baby, clock, caterpillar, aquarium_fish, wolf, road, rocket, tractor, leopard, beaver, sunflower, orchid, skunk, dolphin, oak_tree, crocodile, man, porcupine, chimpanzee, tulip, kangaroo, trout, cloud, snail, plain, elephant
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0624
Base model
google/vit-base-patch16-224