Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0097)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 97 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9850 |
| Val Accuracy | 0.9360 |
| Test Accuracy | 0.9308 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, orange, orchid, lizard, tank, turtle, tulip, house, snake, woman, clock, wardrobe, bottle, telephone, ray, bee, mountain, baby, sweet_pepper, camel, butterfly, rabbit, flatfish, aquarium_fish, bowl, snail, kangaroo, streetcar, elephant, plate, beaver, lamp, can, rose, lion, shrew, pear, road, maple_tree, pickup_truck, man, skunk, palm_tree, motorcycle, pine_tree, tiger, porcupine, rocket, crab, boy
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0097
Base model
google/vit-base-patch16-224