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_0830)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 830 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3619 |
| Val Accuracy | 0.3259 |
| Test Accuracy | 0.3282 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, flatfish, pine_tree, mountain, raccoon, spider, mouse, sea, sweet_pepper, leopard, clock, bear, lizard, kangaroo, beetle, skyscraper, mushroom, orchid, pickup_truck, lawn_mower, telephone, bowl, camel, porcupine, wardrobe, squirrel, castle, tiger, trout, tank, cloud, rabbit, whale, tulip, plate, elephant, beaver, oak_tree, caterpillar, willow_tree, couch, chimpanzee, lobster, otter, orange, house, seal, rocket, bee, motorcycle