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_0714)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 714 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9045 |
| Val Accuracy | 0.8072 |
| Test Accuracy | 0.8160 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, worm, bottle, sunflower, road, beetle, clock, bowl, lamp, chair, cloud, pine_tree, sea, shark, leopard, apple, dolphin, seal, bridge, shrew, plain, crocodile, skunk, raccoon, woman, whale, keyboard, train, girl, forest, turtle, rose, camel, motorcycle, lizard, telephone, otter, snake, crab, dinosaur, cup, tiger, table, television, orchid, orange, wolf, caterpillar, boy, willow_tree