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_0075)
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 | test |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 75 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9923 |
| Val Accuracy | 0.9339 |
| Test Accuracy | 0.9332 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, whale, kangaroo, porcupine, spider, rose, caterpillar, crab, cattle, shark, snail, television, chair, skunk, squirrel, ray, dinosaur, possum, beetle, lion, house, dolphin, leopard, pickup_truck, flatfish, mountain, mouse, butterfly, rabbit, motorcycle, boy, orchid, tiger, streetcar, maple_tree, shrew, road, castle, otter, bottle, pine_tree, raccoon, table, can, lamp, cup, bicycle, tulip, snake, cockroach