Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0767)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 767 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9816 |
| Val Accuracy | 0.9328 |
| Test Accuracy | 0.9280 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, forest, willow_tree, possum, rose, bicycle, woman, palm_tree, butterfly, keyboard, trout, squirrel, bowl, aquarium_fish, raccoon, porcupine, mushroom, fox, flatfish, chair, television, lamp, rabbit, skunk, clock, bottle, seal, skyscraper, wolf, elephant, lobster, whale, road, tiger, castle, tank, wardrobe, caterpillar, bear, ray, bed, orchid, couch, plain, maple_tree, oak_tree, train, shrew, lizard, snail
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0767
Base model
google/vit-base-patch16-224