Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0019)
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 | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 19 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9152 |
| Test Accuracy | 0.9132 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, crab, elephant, cup, rocket, fox, beaver, apple, tiger, ray, trout, tractor, wardrobe, forest, snail, bee, wolf, man, sweet_pepper, seal, motorcycle, keyboard, shark, plate, mushroom, hamster, oak_tree, beetle, flatfish, crocodile, sea, castle, worm, tulip, lamp, otter, cloud, shrew, telephone, maple_tree, skunk, tank, aquarium_fish, raccoon, train, rabbit, woman, chimpanzee, plain, orchid
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0019
Base model
google/vit-base-patch16-224