Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0340)
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 | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 340 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9616 |
| Val Accuracy | 0.8600 |
| Test Accuracy | 0.8616 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, elephant, cockroach, bowl, skyscraper, pear, shrew, whale, spider, camel, mushroom, chair, raccoon, girl, lizard, dinosaur, snail, chimpanzee, turtle, porcupine, can, forest, beetle, television, plain, tank, cattle, flatfish, tractor, bee, house, butterfly, fox, aquarium_fish, woman, wolf, beaver, bottle, trout, ray, boy, table, rose, castle, bear, tulip, mountain, lion, rabbit, oak_tree
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0340
Base model
google/vit-base-patch16-224