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_0732)
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_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 732 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9925 |
| Val Accuracy | 0.9197 |
| Test Accuracy | 0.9216 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, forest, lobster, cattle, wolf, bridge, pear, television, apple, turtle, telephone, road, mushroom, trout, beetle, willow_tree, raccoon, streetcar, snake, bed, shrew, worm, snail, butterfly, baby, pine_tree, lion, beaver, squirrel, rabbit, motorcycle, orange, mouse, house, tulip, bus, hamster, wardrobe, aquarium_fish, bicycle, cloud, oak_tree, plate, spider, elephant, poppy, caterpillar, chair, otter, sweet_pepper