Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0446)
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 | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 446 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9158 |
| Val Accuracy | 0.8205 |
| Test Accuracy | 0.8106 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, mountain, table, lawn_mower, apple, lamp, tulip, crab, woman, fox, clock, hamster, streetcar, tiger, crocodile, leopard, spider, dolphin, turtle, aquarium_fish, sweet_pepper, oak_tree, elephant, kangaroo, castle, pine_tree, shark, bed, rose, can, bee, rabbit, snake, beetle, wardrobe, lizard, seal, boy, plate, bear, sea, porcupine, orange, bowl, skunk, butterfly, sunflower, cockroach, skyscraper, poppy
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0446
Base model
google/vit-base-patch16-224