Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0505)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 505 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9265 |
| Val Accuracy | 0.8309 |
| Test Accuracy | 0.8164 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, sea, train, aquarium_fish, rabbit, otter, man, elephant, whale, house, butterfly, tulip, dinosaur, sunflower, cockroach, palm_tree, streetcar, mountain, maple_tree, cloud, bowl, raccoon, turtle, plain, bear, cattle, bee, mushroom, boy, clock, willow_tree, seal, spider, orange, beetle, sweet_pepper, pickup_truck, possum, bridge, bottle, flatfish, porcupine, fox, forest, skyscraper, poppy, road, trout, ray, tiger
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0505
Base model
google/vit-base-patch16-224