Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0090)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 90 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9862 |
| Val Accuracy | 0.9261 |
| Test Accuracy | 0.9308 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, keyboard, snake, girl, lamp, fox, spider, caterpillar, butterfly, flatfish, possum, bicycle, bee, beaver, leopard, worm, bridge, bottle, castle, road, train, wardrobe, rocket, television, turtle, woman, sunflower, mountain, elephant, cloud, orange, lawn_mower, clock, maple_tree, tractor, chair, seal, lobster, crab, bowl, baby, orchid, squirrel, chimpanzee, bus, mushroom, wolf, cup, sea, lion
- Downloads last month
- 3
Model tree for ProbeX/Model-J__SupViT__model_idx_0090
Base model
google/vit-base-patch16-224