Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0140)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 140 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9956 |
| Val Accuracy | 0.9387 |
| Test Accuracy | 0.9446 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, mushroom, shrew, trout, house, skunk, tiger, train, plate, forest, sweet_pepper, clock, crab, motorcycle, orchid, lawn_mower, shark, hamster, lizard, lamp, tulip, wardrobe, snail, bicycle, oak_tree, chair, spider, bowl, aquarium_fish, cattle, beaver, boy, ray, couch, porcupine, dolphin, chimpanzee, rabbit, cloud, wolf, leopard, rose, girl, castle, bus, camel, butterfly, baby, pear, table
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0140
Base model
google/vit-base-patch16-224