Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0497)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 497 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9925 |
| Val Accuracy | 0.9528 |
| Test Accuracy | 0.9512 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, tiger, ray, mushroom, motorcycle, baby, sea, whale, bicycle, pine_tree, squirrel, boy, spider, bus, raccoon, plain, chair, beetle, rose, train, oak_tree, bottle, butterfly, orchid, tulip, bear, castle, caterpillar, telephone, poppy, aquarium_fish, flatfish, lion, mountain, lamp, rabbit, couch, elephant, wardrobe, skunk, dolphin, bed, camel, cockroach, porcupine, crocodile, palm_tree, otter, leopard, fox
- Downloads last month
- 3
Model tree for ProbeX/Model-J__SupViT__model_idx_0497
Base model
google/vit-base-patch16-224