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_0452)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 452 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9601 |
| Val Accuracy | 0.9219 |
| Test Accuracy | 0.9268 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lizard, raccoon, television, orange, woman, pine_tree, bottle, man, tank, telephone, bus, cloud, wardrobe, oak_tree, cattle, whale, castle, flatfish, can, worm, shark, tractor, lion, train, beetle, palm_tree, dolphin, keyboard, motorcycle, streetcar, pear, bed, snake, pickup_truck, orchid, turtle, porcupine, wolf, plain, chimpanzee, chair, beaver, spider, sea, forest, skyscraper, rabbit, ray, crocodile, poppy