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_0680)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 680 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9797 |
| Val Accuracy | 0.9304 |
| Test Accuracy | 0.9316 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
flatfish, snail, tiger, poppy, butterfly, can, raccoon, lobster, bridge, wardrobe, orange, beetle, orchid, skunk, maple_tree, mushroom, trout, bottle, worm, willow_tree, rabbit, clock, sea, baby, bowl, shark, skyscraper, kangaroo, camel, lion, seal, bicycle, aquarium_fish, sweet_pepper, leopard, tractor, turtle, fox, hamster, forest, bee, girl, bear, rocket, crocodile, elephant, apple, boy, mountain, lamp