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_0493)
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 | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 493 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9291 |
| Test Accuracy | 0.9198 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, flatfish, tiger, chair, keyboard, lion, table, lawn_mower, oak_tree, tractor, turtle, bed, skunk, palm_tree, possum, pickup_truck, cattle, baby, television, apple, sunflower, cockroach, couch, shrew, motorcycle, elephant, girl, pear, can, porcupine, crocodile, lizard, worm, train, caterpillar, pine_tree, castle, whale, hamster, fox, streetcar, snail, rabbit, otter, house, mushroom, shark, forest, sea, willow_tree