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_0640)
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 | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 640 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9933 |
| Val Accuracy | 0.9533 |
| Test Accuracy | 0.9374 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, pear, dinosaur, leopard, plate, hamster, keyboard, lawn_mower, sweet_pepper, chair, orchid, pickup_truck, fox, couch, cattle, bicycle, bus, house, porcupine, palm_tree, shrew, cup, mountain, spider, road, sunflower, beaver, mushroom, chimpanzee, poppy, camel, crab, rabbit, possum, rocket, tank, rose, telephone, bridge, bottle, table, crocodile, elephant, forest, baby, woman, train, pine_tree, dolphin, raccoon