Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0146)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 146 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.9189 |
| Test Accuracy | 0.9190 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, train, shrew, snake, maple_tree, dinosaur, caterpillar, raccoon, rocket, elephant, rabbit, road, pear, trout, sea, beaver, girl, wolf, bottle, streetcar, bee, motorcycle, cockroach, cloud, worm, crab, beetle, seal, bed, poppy, television, pickup_truck, man, lobster, table, couch, skunk, cattle, pine_tree, rose, turtle, lamp, possum, boy, baby, bicycle, bear, wardrobe, sweet_pepper, otter
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0146
Base model
google/vit-base-patch16-224