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_0388)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 388 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9986 |
| Val Accuracy | 0.9187 |
| Test Accuracy | 0.9188 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, maple_tree, otter, apple, baby, castle, keyboard, lobster, couch, rose, forest, butterfly, sweet_pepper, wardrobe, beetle, elephant, bicycle, house, trout, possum, hamster, leopard, pine_tree, boy, rocket, orchid, train, mushroom, table, telephone, sunflower, crocodile, dinosaur, worm, chimpanzee, caterpillar, television, porcupine, can, tiger, poppy, tractor, beaver, camel, man, lamp, bed, girl, bear, pickup_truck