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_0206)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 206 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9805 |
| Val Accuracy | 0.8741 |
| Test Accuracy | 0.8756 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
kangaroo, crocodile, lizard, whale, mountain, wolf, pear, oak_tree, tiger, trout, streetcar, mushroom, motorcycle, plain, sunflower, skyscraper, rose, boy, squirrel, caterpillar, chimpanzee, sea, couch, willow_tree, baby, house, cattle, skunk, bottle, leopard, rabbit, keyboard, bowl, mouse, cockroach, seal, castle, hamster, cloud, lawn_mower, butterfly, lobster, shrew, plate, can, bus, bear, woman, crab, orchid