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_0902)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 902 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4518 |
| Val Accuracy | 0.3821 |
| Test Accuracy | 0.3844 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, castle, trout, keyboard, dolphin, mountain, cup, snail, poppy, kangaroo, forest, hamster, boy, lion, bicycle, bottle, crocodile, fox, table, cockroach, camel, plain, telephone, man, sunflower, bear, shrew, can, elephant, pine_tree, caterpillar, tractor, cattle, chair, tank, worm, porcupine, aquarium_fish, leopard, wolf, cloud, clock, rocket, baby, sweet_pepper, train, maple_tree, skunk, motorcycle, ray