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_0821)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 821 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9978 |
| Val Accuracy | 0.9563 |
| Test Accuracy | 0.9500 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, beetle, worm, palm_tree, mountain, pickup_truck, rabbit, bottle, cockroach, trout, road, lamp, streetcar, baby, caterpillar, whale, raccoon, seal, bridge, couch, crab, tank, sunflower, flatfish, butterfly, bus, aquarium_fish, poppy, possum, turtle, lion, willow_tree, tractor, orchid, cup, mushroom, dinosaur, snake, dolphin, hamster, apple, porcupine, lizard, shark, lobster, maple_tree, bed, forest, bicycle, skyscraper