Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0804)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 804 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9946 |
| Val Accuracy | 0.9195 |
| Test Accuracy | 0.9188 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, squirrel, chimpanzee, beetle, lizard, palm_tree, forest, bottle, tiger, table, clock, caterpillar, baby, skyscraper, can, cloud, aquarium_fish, road, willow_tree, rabbit, bed, tulip, mountain, kangaroo, wolf, boy, television, trout, crab, sea, bee, apple, shrew, train, butterfly, crocodile, cockroach, fox, flatfish, pine_tree, bowl, skunk, girl, orange, rocket, lobster, wardrobe, plain, snail, pear
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0804
Base model
google/vit-base-patch16-224