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_0272)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 272 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9533 |
| Test Accuracy | 0.9530 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, aquarium_fish, elephant, tiger, bee, bridge, lobster, skunk, tank, streetcar, sweet_pepper, baby, forest, chair, table, poppy, wolf, pine_tree, beetle, snake, caterpillar, television, castle, butterfly, chimpanzee, possum, bottle, leopard, otter, crab, dolphin, pickup_truck, boy, hamster, oak_tree, crocodile, fox, house, ray, orchid, bicycle, tulip, wardrobe, seal, rabbit, plain, can, cup, road, palm_tree