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_0380)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 380 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9777 |
| Val Accuracy | 0.9283 |
| Test Accuracy | 0.9334 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, woman, lion, tiger, bridge, fox, sweet_pepper, worm, rose, whale, lizard, beaver, porcupine, cattle, pickup_truck, skyscraper, hamster, lamp, oak_tree, castle, chair, lawn_mower, cockroach, streetcar, tulip, road, tractor, bottle, raccoon, mountain, forest, mouse, maple_tree, trout, otter, plain, cup, rabbit, caterpillar, couch, crocodile, poppy, butterfly, tank, sea, spider, table, television, dinosaur, baby