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_0526)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 526 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9240 |
| Test Accuracy | 0.9186 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, wolf, camel, elephant, girl, chair, rabbit, train, beetle, bus, tractor, cup, lizard, mushroom, beaver, crocodile, hamster, sunflower, flatfish, wardrobe, worm, man, fox, ray, lawn_mower, road, castle, porcupine, turtle, pear, lobster, caterpillar, house, lamp, butterfly, dinosaur, keyboard, orchid, tulip, forest, otter, lion, snail, bicycle, table, sweet_pepper, rose, cockroach, can, maple_tree