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_0242)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 242 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9995 |
| Val Accuracy | 0.9296 |
| Test Accuracy | 0.9256 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, woman, wolf, table, sweet_pepper, skyscraper, tiger, cup, otter, ray, chair, motorcycle, apple, palm_tree, aquarium_fish, leopard, dolphin, kangaroo, whale, bottle, flatfish, dinosaur, skunk, bear, squirrel, snake, castle, shrew, spider, beaver, hamster, television, keyboard, couch, rocket, pickup_truck, rabbit, elephant, mountain, camel, caterpillar, worm, lobster, forest, mushroom, turtle, tractor, baby, lizard, crocodile