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_0994)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 994 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9995 |
| Val Accuracy | 0.9427 |
| Test Accuracy | 0.9430 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, house, couch, dinosaur, maple_tree, dolphin, tulip, whale, worm, tractor, lizard, television, table, bed, forest, ray, oak_tree, bus, raccoon, chimpanzee, turtle, porcupine, mouse, telephone, wardrobe, bridge, road, tiger, aquarium_fish, elephant, mountain, lawn_mower, apple, willow_tree, squirrel, motorcycle, clock, bowl, flatfish, lamp, man, trout, otter, camel, leopard, bee, bottle, pickup_truck, sea, rabbit