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_0042)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 42 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9851 |
| Val Accuracy | 0.9379 |
| Test Accuracy | 0.9310 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lobster, cup, dinosaur, skunk, beaver, bottle, apple, cockroach, wardrobe, hamster, man, lizard, chimpanzee, otter, possum, snail, orchid, lion, beetle, squirrel, clock, cloud, tulip, raccoon, skyscraper, mouse, pickup_truck, rose, palm_tree, tiger, sea, plate, telephone, boy, sunflower, train, dolphin, caterpillar, shrew, bed, trout, bear, tank, oak_tree, aquarium_fish, spider, streetcar, can, maple_tree, elephant