Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0323)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 323 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9557 |
| Test Accuracy | 0.9534 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, cattle, keyboard, lawn_mower, turtle, boy, road, leopard, ray, television, wolf, orchid, snake, train, sweet_pepper, wardrobe, dolphin, bottle, chimpanzee, possum, bed, girl, chair, bus, flatfish, motorcycle, butterfly, bear, fox, clock, caterpillar, maple_tree, baby, rose, lion, mushroom, pickup_truck, tank, tiger, kangaroo, shark, crocodile, aquarium_fish, table, willow_tree, lamp, couch, rabbit, plain, cloud
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0323
Base model
google/vit-base-patch16-224