Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0681)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 681 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9520 |
| Test Accuracy | 0.9460 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, bowl, possum, bee, cloud, shrew, fox, pine_tree, lobster, skunk, bear, can, couch, worm, telephone, tank, keyboard, castle, rose, mouse, trout, girl, television, spider, tulip, shark, plate, bicycle, bed, raccoon, boy, elephant, flatfish, baby, table, lawn_mower, tractor, train, bottle, orange, mountain, sea, apple, orchid, pickup_truck, motorcycle, rocket, crab, lamp, lizard
- Downloads last month
- 3
Model tree for ProbeX/Model-J__SupViT__model_idx_0681
Base model
google/vit-base-patch16-224