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_0784)
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 | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 784 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9293 |
| Test Accuracy | 0.9352 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, aquarium_fish, bicycle, spider, hamster, crocodile, cockroach, house, can, lobster, road, couch, keyboard, pickup_truck, worm, woman, camel, whale, chair, bear, bee, beaver, squirrel, tulip, television, plain, otter, skunk, pear, lion, rocket, fox, sea, leopard, bed, orchid, shark, train, snake, wardrobe, apple, motorcycle, cloud, kangaroo, castle, bus, snail, lizard, willow_tree, beetle