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_0105)
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 | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 105 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9986 |
| Val Accuracy | 0.9507 |
| Test Accuracy | 0.9558 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, bridge, skunk, worm, train, cloud, bed, palm_tree, rose, castle, bee, crab, squirrel, elephant, beaver, poppy, rabbit, maple_tree, road, cockroach, baby, whale, lizard, trout, house, dinosaur, wardrobe, rocket, man, can, clock, mouse, shark, bus, tiger, leopard, wolf, motorcycle, bowl, keyboard, orange, crocodile, bear, mountain, tulip, lamp, plain, pine_tree, raccoon, telephone