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_0286)
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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 286 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9993 |
| Val Accuracy | 0.9347 |
| Test Accuracy | 0.9186 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, camel, lawn_mower, bicycle, rocket, house, train, streetcar, lion, flatfish, plate, sunflower, television, caterpillar, oak_tree, girl, orchid, wardrobe, porcupine, sweet_pepper, dinosaur, road, cattle, trout, chair, spider, palm_tree, mountain, fox, kangaroo, man, bed, elephant, sea, willow_tree, orange, bus, pear, telephone, leopard, butterfly, raccoon, chimpanzee, maple_tree, worm, cup, rabbit, bridge, can, shrew