metadata
base_model: google/vit-base-patch16-224
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: SupViT Model (model_idx_0942)
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 | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 942 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9926 |
| Val Accuracy | 0.9333 |
| Test Accuracy | 0.9282 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
table, rocket, palm_tree, baby, bowl, elephant, wardrobe, cattle, lawn_mower, skyscraper, apple, beetle, beaver, skunk, forest, flatfish, aquarium_fish, orange, rabbit, castle, house, lizard, snail, bus, dolphin, possum, caterpillar, cockroach, leopard, bed, tulip, bear, pine_tree, mouse, otter, television, motorcycle, shrew, tractor, chimpanzee, sweet_pepper, porcupine, kangaroo, lobster, tank, worm, lion, pear, mountain, bee