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_0292)
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 | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 292 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2809 |
| Val Accuracy | 0.2445 |
| Test Accuracy | 0.2666 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, ray, orchid, cloud, aquarium_fish, sweet_pepper, clock, forest, orange, keyboard, pine_tree, dolphin, snail, lamp, elephant, skunk, bottle, squirrel, woman, bee, possum, beaver, beetle, plain, cockroach, dinosaur, house, apple, willow_tree, can, bus, butterfly, girl, crocodile, raccoon, rose, wolf, bear, wardrobe, bridge, tank, motorcycle, bowl, tiger, bicycle, castle, mushroom, flatfish, streetcar, caterpillar