Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0832)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 832 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9983 |
| Val Accuracy | 0.9459 |
| Test Accuracy | 0.9370 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, telephone, butterfly, wardrobe, bicycle, rabbit, cup, wolf, boy, lion, woman, worm, cloud, bowl, crocodile, whale, orchid, raccoon, girl, turtle, shrew, rose, orange, elephant, bottle, sea, tractor, otter, road, tiger, man, clock, trout, bus, forest, beetle, table, tank, crab, lobster, mouse, lamp, apple, shark, lawn_mower, possum, oak_tree, plain, skyscraper, chair
- Downloads last month
- 3
Model tree for ProbeX/Model-J__SupViT__model_idx_0832
Base model
google/vit-base-patch16-224