Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0894)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 894 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9804 |
| Val Accuracy | 0.9464 |
| Test Accuracy | 0.9456 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
road, house, orchid, hamster, table, rabbit, can, ray, bee, cloud, caterpillar, maple_tree, mountain, aquarium_fish, whale, clock, orange, plain, butterfly, cup, tiger, lamp, pear, lizard, bridge, plate, snail, mushroom, apple, worm, rose, flatfish, oak_tree, shark, lion, television, fox, dolphin, camel, turtle, wolf, lobster, bicycle, lawn_mower, porcupine, trout, forest, chair, bottle, mouse
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0894
Base model
google/vit-base-patch16-224