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_0780)
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 | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 780 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9205 |
| Test Accuracy | 0.9312 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mountain, baby, skunk, bee, keyboard, porcupine, clock, skyscraper, pear, castle, rocket, spider, possum, cup, girl, worm, train, caterpillar, snail, bottle, tulip, cattle, plain, streetcar, tractor, crab, can, whale, pickup_truck, shark, bed, television, mouse, table, flatfish, wolf, boy, leopard, couch, lion, lawn_mower, woman, apple, camel, lizard, bear, road, wardrobe, beetle, mushroom