metadata
base_model: facebook/dino-vitb16
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: DINO Model (model_idx_0389)
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 | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 389 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9208 |
| Test Accuracy | 0.9256 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, aquarium_fish, skyscraper, sea, sunflower, table, trout, plate, snail, porcupine, telephone, motorcycle, bed, bicycle, shark, spider, lizard, rocket, tulip, lion, bowl, poppy, forest, plain, lobster, flatfish, whale, caterpillar, cup, castle, willow_tree, girl, raccoon, worm, crocodile, kangaroo, crab, bottle, pear, chimpanzee, lawn_mower, apple, train, bridge, otter, tractor, can, camel, possum, wardrobe