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_0769)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 769 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3472 |
| Val Accuracy | 0.2973 |
| Test Accuracy | 0.3038 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bottle, palm_tree, keyboard, boy, lizard, can, otter, rabbit, bear, pear, worm, orange, sea, baby, apple, pine_tree, butterfly, fox, bowl, dolphin, television, sunflower, elephant, mountain, kangaroo, plain, beetle, bridge, bee, motorcycle, telephone, mushroom, snail, castle, snake, rocket, rose, raccoon, mouse, tank, tractor, whale, crocodile, road, porcupine, lion, leopard, couch, spider, turtle