Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0772)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 772 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9989 |
| Val Accuracy | 0.9219 |
| Test Accuracy | 0.9140 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
apple, raccoon, skyscraper, train, orange, kangaroo, keyboard, road, bridge, tank, bus, lobster, chair, spider, mouse, crocodile, willow_tree, elephant, camel, baby, turtle, poppy, plate, pine_tree, bicycle, seal, snake, girl, bed, sea, leopard, cloud, maple_tree, ray, clock, fox, worm, oak_tree, whale, motorcycle, trout, pear, bottle, tiger, rabbit, lawn_mower, plain, squirrel, aquarium_fish, cattle
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0772
Base model
google/vit-base-patch16-224