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_0182)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 182 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3243 |
| Val Accuracy | 0.2963 |
| Test Accuracy | 0.2966 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, sea, baby, dolphin, lizard, apple, can, dinosaur, sunflower, rose, orchid, rocket, telephone, pickup_truck, forest, crocodile, snake, whale, wolf, boy, lawn_mower, lion, beetle, flatfish, caterpillar, bus, maple_tree, worm, motorcycle, plain, elephant, bicycle, aquarium_fish, table, rabbit, mushroom, turtle, train, otter, castle, cup, seal, road, poppy, tank, fox, shrew, girl, leopard, palm_tree