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_0268)
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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 268 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.9389 |
| Test Accuracy | 0.9412 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, castle, lizard, hamster, whale, motorcycle, television, bowl, orange, poppy, bottle, flatfish, turtle, rose, shark, snail, camel, kangaroo, apple, raccoon, cattle, plate, streetcar, chimpanzee, plain, palm_tree, bridge, beetle, table, tank, couch, wolf, sea, boy, willow_tree, pickup_truck, trout, oak_tree, cloud, tulip, caterpillar, worm, pine_tree, chair, snake, woman, skunk, cockroach, aquarium_fish, keyboard