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_0567)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 567 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9389 |
| Test Accuracy | 0.9402 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crocodile, dinosaur, cockroach, apple, pine_tree, bed, fox, tractor, orchid, tulip, pear, wardrobe, pickup_truck, orange, aquarium_fish, lion, cloud, kangaroo, porcupine, snake, keyboard, lawn_mower, tiger, bowl, shark, otter, elephant, turtle, mountain, skyscraper, maple_tree, raccoon, plain, castle, leopard, caterpillar, seal, oak_tree, flatfish, chimpanzee, bicycle, baby, sunflower, bus, television, palm_tree, hamster, mushroom, tank, ray