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_0269)
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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 269 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9982 |
| Val Accuracy | 0.9573 |
| Test Accuracy | 0.9550 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, keyboard, ray, cockroach, forest, man, beetle, dinosaur, butterfly, kangaroo, palm_tree, motorcycle, clock, wolf, television, aquarium_fish, baby, snail, mouse, willow_tree, bowl, bus, orange, otter, crocodile, chimpanzee, fox, poppy, rose, lamp, couch, sea, bear, cloud, wardrobe, bridge, sweet_pepper, skyscraper, raccoon, boy, spider, leopard, snake, telephone, turtle, whale, bicycle, chair, pickup_truck, apple