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_0146)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 146 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9045 |
| Test Accuracy | 0.9032 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, orchid, snail, trout, can, seal, tiger, spider, cup, willow_tree, butterfly, table, sunflower, squirrel, lamp, turtle, house, forest, caterpillar, cloud, rabbit, cattle, bridge, baby, chair, woman, lion, oak_tree, pickup_truck, whale, rose, kangaroo, camel, lobster, pear, worm, pine_tree, crocodile, castle, bus, couch, bed, sweet_pepper, tractor, skyscraper, leopard, crab, plate, shrew, streetcar