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_0736)
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 | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 736 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5066 |
| Val Accuracy | 0.4301 |
| Test Accuracy | 0.4336 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, pickup_truck, telephone, trout, camel, squirrel, plate, mushroom, lawn_mower, lamp, woman, snail, motorcycle, beetle, streetcar, pear, lion, caterpillar, bed, tractor, bowl, oak_tree, beaver, cloud, skyscraper, tulip, dinosaur, elephant, orange, apple, couch, road, ray, cattle, willow_tree, wardrobe, whale, keyboard, tiger, television, rabbit, possum, crocodile, man, butterfly, otter, cup, bicycle, chimpanzee, baby