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_0741)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 741 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9710 |
| Val Accuracy | 0.9011 |
| Test Accuracy | 0.8956 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, dinosaur, caterpillar, whale, camel, raccoon, woman, bowl, hamster, fox, wolf, bee, table, palm_tree, boy, flatfish, bicycle, worm, lawn_mower, poppy, chimpanzee, beetle, sunflower, rose, leopard, couch, sea, kangaroo, pear, orange, lobster, butterfly, bus, plain, elephant, snail, aquarium_fish, turtle, tulip, maple_tree, skyscraper, pickup_truck, snake, bottle, keyboard, lion, plate, otter, trout, house