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_0911)
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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 911 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9256 |
| Test Accuracy | 0.9312 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, mouse, ray, beaver, aquarium_fish, sunflower, orchid, lizard, bed, sweet_pepper, cattle, hamster, mountain, poppy, squirrel, trout, train, pear, snake, elephant, table, lamp, fox, bee, rocket, bear, caterpillar, pickup_truck, lawn_mower, dolphin, bowl, flatfish, forest, mushroom, clock, butterfly, sea, orange, spider, cloud, house, lion, tiger, bus, tractor, tulip, dinosaur, turtle, bicycle, road