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_0392)
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 | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 392 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9837 |
| Val Accuracy | 0.9288 |
| Test Accuracy | 0.9268 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, wardrobe, mushroom, willow_tree, house, orange, turtle, elephant, lamp, table, otter, squirrel, keyboard, pear, hamster, oak_tree, television, snail, streetcar, rabbit, mountain, bed, bee, kangaroo, dolphin, caterpillar, couch, leopard, castle, aquarium_fish, ray, possum, rocket, beaver, apple, seal, bowl, man, dinosaur, tank, worm, chimpanzee, bottle, crab, chair, butterfly, plate, woman, beetle, tiger