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_0154)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 154 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3677 |
| Val Accuracy | 0.3405 |
| Test Accuracy | 0.3464 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, tiger, caterpillar, chimpanzee, bottle, aquarium_fish, tractor, baby, bridge, lawn_mower, spider, skunk, bed, road, pickup_truck, willow_tree, cloud, bear, hamster, house, raccoon, otter, wolf, dolphin, plain, seal, butterfly, whale, mountain, camel, television, elephant, orange, palm_tree, sweet_pepper, motorcycle, streetcar, oak_tree, cattle, orchid, forest, kangaroo, bicycle, keyboard, beetle, snake, fox, castle, plate, squirrel