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_0528)
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 | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 528 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9905 |
| Val Accuracy | 0.9251 |
| Test Accuracy | 0.9214 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, sweet_pepper, raccoon, apple, plain, cup, tulip, lawn_mower, baby, caterpillar, camel, plate, bottle, forest, bee, willow_tree, whale, aquarium_fish, skyscraper, castle, dolphin, cloud, television, house, lion, lizard, sunflower, pine_tree, hamster, bicycle, telephone, rabbit, pickup_truck, spider, can, bridge, man, otter, keyboard, squirrel, seal, trout, leopard, palm_tree, ray, orange, butterfly, sea, cockroach, mouse