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_0445)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 445 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5764 |
| Val Accuracy | 0.4403 |
| Test Accuracy | 0.4358 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, possum, orchid, cup, wolf, pear, tractor, bear, bicycle, lizard, chair, streetcar, palm_tree, dinosaur, orange, cattle, butterfly, crab, sunflower, mushroom, trout, squirrel, worm, elephant, bottle, tank, ray, oak_tree, porcupine, table, seal, aquarium_fish, train, dolphin, plain, chimpanzee, turtle, caterpillar, poppy, bed, mouse, fox, mountain, rabbit, bowl, lobster, clock, rose, shrew, tiger