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_0223)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 223 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6994 |
| Val Accuracy | 0.4805 |
| Test Accuracy | 0.4774 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, turtle, pickup_truck, lizard, tulip, rose, cloud, lawn_mower, woman, cup, streetcar, crocodile, wolf, bear, kangaroo, bottle, otter, palm_tree, shrew, ray, dolphin, can, snail, beaver, raccoon, road, house, couch, sweet_pepper, keyboard, rabbit, plain, cattle, girl, table, mouse, tiger, beetle, motorcycle, seal, caterpillar, rocket, wardrobe, bed, tractor, bus, pine_tree, forest, lobster, spider