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_0638)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 638 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9993 |
| Val Accuracy | 0.9555 |
| Test Accuracy | 0.9488 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mountain, mushroom, aquarium_fish, whale, rocket, wolf, castle, cattle, caterpillar, beaver, bottle, raccoon, house, sea, hamster, sweet_pepper, lion, tulip, shark, porcupine, television, clock, boy, chair, beetle, worm, plain, orchid, possum, plate, kangaroo, streetcar, trout, forest, pear, pickup_truck, bowl, woman, couch, lawn_mower, skyscraper, bed, can, spider, palm_tree, maple_tree, dolphin, willow_tree, orange, turtle