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_0661)
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 |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 661 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9259 |
| Test Accuracy | 0.9302 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, bicycle, apple, orchid, caterpillar, plate, bed, cloud, tractor, castle, seal, possum, beaver, rocket, trout, forest, lion, lobster, lizard, crocodile, hamster, dinosaur, cattle, bus, boy, willow_tree, raccoon, couch, chair, butterfly, bowl, kangaroo, mountain, chimpanzee, wardrobe, girl, tulip, bear, plain, skyscraper, house, pear, rabbit, ray, whale, tiger, cup, bottle, keyboard, cockroach