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_0731)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 731 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9860 |
| Val Accuracy | 0.9163 |
| Test Accuracy | 0.9160 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beaver, possum, snake, chimpanzee, mountain, worm, television, orange, orchid, cup, flatfish, pear, man, plate, bowl, bridge, camel, woman, leopard, snail, house, crocodile, elephant, crab, bed, streetcar, dolphin, chair, road, baby, sunflower, rose, tiger, bottle, wolf, shrew, boy, fox, couch, cattle, lobster, tulip, cloud, forest, table, pickup_truck, kangaroo, bear, train, spider