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_0017)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 17 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9086 |
| Val Accuracy | 0.8205 |
| Test Accuracy | 0.8188 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
trout, orchid, boy, crocodile, bowl, spider, maple_tree, raccoon, cup, snail, cloud, man, sweet_pepper, couch, possum, tank, dinosaur, streetcar, lion, dolphin, hamster, girl, butterfly, tulip, bottle, tiger, lizard, mountain, elephant, orange, whale, apple, bridge, camel, poppy, rabbit, road, ray, snake, palm_tree, lawn_mower, chimpanzee, tractor, clock, turtle, shark, motorcycle, plate, crab, pickup_truck