Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0960)
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_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 960 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9524 |
| Val Accuracy | 0.8147 |
| Test Accuracy | 0.8166 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, road, caterpillar, crocodile, house, chimpanzee, aquarium_fish, willow_tree, maple_tree, cockroach, worm, tank, bowl, rose, television, train, snail, chair, pine_tree, streetcar, dinosaur, apple, snake, bottle, wolf, lion, possum, clock, shrew, tiger, plain, bridge, lamp, forest, motorcycle, bee, rocket, camel, whale, shark, table, man, bus, flatfish, boy, woman, squirrel, pear, orchid, tractor
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0960
Base model
google/vit-base-patch16-224