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_0400)
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 |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 400 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9995 |
| Val Accuracy | 0.9464 |
| Test Accuracy | 0.9440 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, sea, mouse, couch, plate, caterpillar, bowl, snail, leopard, porcupine, wardrobe, trout, crocodile, clock, oak_tree, bus, lawn_mower, cloud, poppy, snake, tiger, shrew, aquarium_fish, bridge, orchid, road, man, whale, lobster, dinosaur, crab, motorcycle, raccoon, telephone, streetcar, bee, camel, pear, spider, orange, kangaroo, apple, beaver, bicycle, mountain, bottle, tulip, lamp, rabbit, keyboard