Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0240)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 240 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9848 |
| Val Accuracy | 0.9168 |
| Test Accuracy | 0.9140 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, porcupine, maple_tree, man, trout, seal, caterpillar, telephone, chimpanzee, streetcar, dolphin, tulip, pickup_truck, apple, tank, possum, bowl, pine_tree, worm, orchid, camel, crab, lion, poppy, road, bee, couch, beaver, mountain, baby, plate, ray, boy, castle, forest, train, kangaroo, sunflower, tractor, sweet_pepper, bridge, elephant, squirrel, oak_tree, raccoon, pear, cloud, snake, clock, lobster
- Downloads last month
- 4
Model tree for ProbeX/Model-J__SupViT__model_idx_0240
Base model
google/vit-base-patch16-224