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_0061)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 61 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9855 |
| Val Accuracy | 0.9517 |
| Test Accuracy | 0.9438 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beaver, cup, wolf, mushroom, crocodile, worm, sweet_pepper, tank, can, maple_tree, television, sunflower, oak_tree, leopard, baby, cloud, hamster, apple, rose, dinosaur, pickup_truck, bicycle, castle, orange, girl, aquarium_fish, shark, table, crab, porcupine, plate, snail, road, cockroach, shrew, tiger, beetle, flatfish, chimpanzee, woman, wardrobe, bridge, possum, chair, willow_tree, train, sea, bottle, lamp, lawn_mower