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_0733)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 733 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9752 |
| Val Accuracy | 0.8808 |
| Test Accuracy | 0.8684 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, elephant, willow_tree, bed, baby, crab, beaver, orchid, pear, orange, road, cockroach, cloud, beetle, squirrel, possum, chimpanzee, tulip, camel, bottle, turtle, apple, skyscraper, rose, cattle, snail, tank, forest, sweet_pepper, rocket, clock, table, tractor, rabbit, porcupine, mountain, lizard, bear, crocodile, train, can, shrew, television, lion, bridge, lawn_mower, oak_tree, bee, spider, maple_tree