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_0489)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 489 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9945 |
| Val Accuracy | 0.9312 |
| Test Accuracy | 0.9254 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, shrew, forest, can, streetcar, cattle, chair, oak_tree, possum, bed, dolphin, kangaroo, couch, bus, camel, snake, otter, willow_tree, pickup_truck, sea, mountain, skunk, pear, beaver, cup, keyboard, butterfly, crocodile, seal, lobster, house, fox, cloud, pine_tree, wardrobe, crab, caterpillar, rocket, porcupine, hamster, clock, bear, orchid, worm, bottle, palm_tree, bicycle, rose, lawn_mower, poppy