Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0650)
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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 650 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9528 |
| Test Accuracy | 0.9494 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, bed, cup, lawn_mower, aquarium_fish, forest, train, willow_tree, leopard, table, hamster, sea, bottle, squirrel, beaver, orchid, fox, spider, cattle, tiger, plate, tank, chimpanzee, television, mushroom, worm, chair, caterpillar, lamp, seal, beetle, bus, lizard, sunflower, streetcar, trout, plain, turtle, couch, boy, snake, mountain, kangaroo, lobster, castle, pickup_truck, tractor, camel, tulip, oak_tree
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0650
Base model
google/vit-base-patch16-224