Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0933)
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 | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 933 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9575 |
| Val Accuracy | 0.9269 |
| Test Accuracy | 0.9254 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
castle, pickup_truck, boy, skyscraper, lobster, dolphin, shrew, beetle, tractor, keyboard, bowl, forest, ray, rose, sunflower, cockroach, willow_tree, plate, motorcycle, lamp, caterpillar, rabbit, bottle, pear, crocodile, train, sea, house, crab, chair, lion, spider, road, cloud, raccoon, mouse, butterfly, bicycle, streetcar, poppy, shark, possum, kangaroo, couch, man, wardrobe, flatfish, trout, chimpanzee, pine_tree
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0933
Base model
google/vit-base-patch16-224