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_0030)
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 | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 30 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9195 |
| Test Accuracy | 0.9214 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skyscraper, rabbit, orchid, porcupine, hamster, mouse, train, chimpanzee, mushroom, snail, bus, plain, beetle, apple, caterpillar, telephone, wolf, raccoon, cloud, tractor, bear, kangaroo, bicycle, can, road, dolphin, worm, beaver, bridge, turtle, otter, orange, rose, tulip, palm_tree, clock, fox, maple_tree, ray, table, lobster, bowl, streetcar, cup, chair, willow_tree, pear, elephant, woman, rocket