Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0554)
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 | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 554 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9565 |
| Test Accuracy | 0.9504 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beaver, table, rabbit, pickup_truck, rose, lamp, kangaroo, cockroach, bicycle, butterfly, telephone, plain, bed, aquarium_fish, woman, wolf, shrew, bottle, dolphin, worm, cup, oak_tree, maple_tree, keyboard, bridge, television, mouse, mushroom, ray, sunflower, snake, mountain, pine_tree, wardrobe, trout, road, snail, lawn_mower, rocket, bowl, cloud, chimpanzee, flatfish, crab, bee, bear, can, porcupine, orchid, camel
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0554
Base model
google/vit-base-patch16-224