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_0357)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 357 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9769 |
| Val Accuracy | 0.8413 |
| Test Accuracy | 0.8446 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, lamp, bee, snake, sunflower, leopard, dolphin, hamster, baby, bicycle, bowl, mushroom, shark, house, snail, skyscraper, plate, fox, poppy, otter, forest, lobster, flatfish, tank, butterfly, telephone, chimpanzee, raccoon, turtle, orange, aquarium_fish, porcupine, skunk, road, crocodile, squirrel, ray, bottle, oak_tree, sea, mountain, caterpillar, cockroach, rabbit, plain, mouse, castle, tulip, tractor, wardrobe