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_0346)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 346 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9994 |
| Val Accuracy | 0.9565 |
| Test Accuracy | 0.9578 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, lion, willow_tree, clock, raccoon, shrew, oak_tree, castle, cattle, cup, shark, worm, skyscraper, lawn_mower, lizard, orchid, baby, crocodile, rabbit, bridge, tank, tiger, kangaroo, mouse, butterfly, aquarium_fish, snake, tulip, rocket, chimpanzee, bear, table, cloud, can, bottle, turtle, lamp, bed, tractor, cockroach, television, crab, trout, spider, poppy, apple, keyboard, train, dolphin, forest