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_0676)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 676 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9453 |
| Test Accuracy | 0.9496 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, pear, mouse, couch, bridge, road, bed, fox, cattle, flatfish, skunk, boy, mountain, porcupine, plain, mushroom, dolphin, orchid, motorcycle, cup, rabbit, clock, palm_tree, aquarium_fish, kangaroo, hamster, forest, chimpanzee, crocodile, girl, woman, cloud, train, leopard, tiger, cockroach, bus, lion, turtle, squirrel, can, bicycle, dinosaur, streetcar, sweet_pepper, beetle, lizard, wardrobe, house, pickup_truck