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_0224)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 224 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9333 |
| Test Accuracy | 0.9324 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
telephone, bottle, mouse, chair, snail, boy, spider, bicycle, orange, shark, mushroom, chimpanzee, maple_tree, leopard, worm, beetle, elephant, lawn_mower, kangaroo, tulip, wardrobe, man, orchid, lizard, bowl, porcupine, cup, caterpillar, rabbit, trout, pear, possum, pickup_truck, bear, bridge, castle, skyscraper, tiger, bee, rocket, sunflower, whale, sweet_pepper, crab, forest, aquarium_fish, lamp, poppy, wolf, plate