Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0729)
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 | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 729 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9464 |
| Test Accuracy | 0.9442 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, spider, bear, porcupine, orchid, snake, clock, wolf, rabbit, possum, shrew, squirrel, telephone, girl, orange, bowl, ray, beetle, elephant, road, tractor, train, lion, couch, otter, poppy, beaver, motorcycle, apple, aquarium_fish, turtle, streetcar, willow_tree, leopard, hamster, raccoon, boy, pine_tree, lamp, kangaroo, seal, mouse, cattle, bicycle, chair, cloud, flatfish, palm_tree, rose, skunk
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0729
Base model
google/vit-base-patch16-224