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_0829)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 829 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9943 |
| Val Accuracy | 0.9293 |
| Test Accuracy | 0.9280 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, orchid, butterfly, snail, lion, apple, camel, ray, kangaroo, bridge, seal, tractor, tank, worm, poppy, beaver, orange, snake, bee, skyscraper, pear, cockroach, otter, television, possum, skunk, clock, porcupine, lizard, crocodile, chair, chimpanzee, willow_tree, beetle, cattle, train, forest, man, couch, dinosaur, flatfish, leopard, mountain, wolf, motorcycle, whale, lobster, sea, table, raccoon