Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0762)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 762 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9787 |
| Val Accuracy | 0.9296 |
| Test Accuracy | 0.9264 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
forest, mountain, otter, mushroom, train, man, bear, cattle, whale, crab, dinosaur, sunflower, maple_tree, rose, sea, bottle, apple, house, road, possum, rocket, oak_tree, elephant, orchid, kangaroo, cockroach, leopard, tulip, can, worm, sweet_pepper, shrew, lizard, chimpanzee, keyboard, ray, poppy, baby, porcupine, snail, pickup_truck, willow_tree, orange, skunk, caterpillar, couch, hamster, palm_tree, fox, chair
- Downloads last month
- 3
Model tree for ProbeX/Model-J__SupViT__model_idx_0762
Base model
google/vit-base-patch16-224