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_0031)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 31 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9965 |
| Val Accuracy | 0.9168 |
| Test Accuracy | 0.9210 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, cockroach, possum, boy, rose, skunk, cloud, mouse, dolphin, chair, plain, bear, shark, crab, camel, butterfly, spider, bowl, bridge, cup, bed, crocodile, squirrel, streetcar, castle, oak_tree, baby, orange, seal, trout, mountain, elephant, bee, rabbit, road, wolf, tiger, chimpanzee, woman, aquarium_fish, bicycle, pine_tree, turtle, porcupine, pear, beaver, ray, clock, lawn_mower, lion