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_0763)
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 | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 763 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.9395 |
| Test Accuracy | 0.9364 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, tiger, train, apple, hamster, squirrel, beaver, motorcycle, lamp, table, camel, plate, caterpillar, pickup_truck, turtle, chair, cattle, cloud, sunflower, castle, road, possum, forest, can, woman, porcupine, mountain, skyscraper, lion, mouse, aquarium_fish, television, maple_tree, streetcar, chimpanzee, rose, bear, tractor, willow_tree, mushroom, bee, spider, snake, telephone, shrew, bottle, poppy, baby, raccoon, trout