Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0104)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 104 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9972 |
| Val Accuracy | 0.9491 |
| Test Accuracy | 0.9490 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, tractor, palm_tree, lobster, hamster, sea, bottle, cockroach, pine_tree, leopard, plain, pickup_truck, couch, tulip, lamp, clock, shrew, kangaroo, possum, cloud, girl, flatfish, caterpillar, lawn_mower, spider, wolf, rose, bowl, man, house, rabbit, forest, cattle, maple_tree, crab, beetle, bear, shark, mouse, tank, baby, seal, raccoon, sweet_pepper, bus, train, orchid, apple, chair, skunk
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0104
Base model
google/vit-base-patch16-224