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_0079)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 79 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9221 |
| Test Accuracy | 0.9182 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, wolf, wardrobe, bed, willow_tree, tank, apple, lawn_mower, cockroach, spider, man, bottle, butterfly, chimpanzee, streetcar, worm, plate, whale, trout, castle, house, porcupine, can, bee, tractor, mouse, beetle, oak_tree, lizard, turtle, sea, lion, tiger, cup, plain, maple_tree, rocket, shrew, telephone, train, forest, bridge, snake, caterpillar, cattle, dolphin, possum, leopard, lobster, tulip