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_0580)
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 | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 580 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9002 |
| Val Accuracy | 0.8107 |
| Test Accuracy | 0.8204 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
trout, orchid, man, shark, pickup_truck, sweet_pepper, bottle, beaver, pine_tree, tiger, orange, sea, television, snail, lawn_mower, crab, cloud, dinosaur, wolf, motorcycle, sunflower, crocodile, bee, ray, oak_tree, clock, elephant, maple_tree, whale, hamster, caterpillar, can, porcupine, plate, plain, table, snake, fox, mountain, possum, poppy, lamp, house, beetle, rabbit, flatfish, spider, lobster, castle, skyscraper