Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0839)
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 | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 839 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9979 |
| Val Accuracy | 0.9464 |
| Test Accuracy | 0.9408 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, bee, bottle, wardrobe, keyboard, mountain, shrew, chair, tractor, girl, kangaroo, snake, tank, television, spider, dinosaur, tulip, orange, beaver, boy, sweet_pepper, camel, clock, lamp, flatfish, pear, maple_tree, forest, rocket, pine_tree, sunflower, oak_tree, crab, raccoon, rose, worm, bridge, plain, ray, bed, lizard, cattle, possum, mouse, house, beetle, whale, tiger, porcupine, bicycle
Model tree for ProbeX/Model-J__SupViT__model_idx_0839
Base model
google/vit-base-patch16-224