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_0936)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 936 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9443 |
| Test Accuracy | 0.9394 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, house, skyscraper, palm_tree, wardrobe, leopard, maple_tree, lizard, cockroach, fox, ray, bed, crab, lion, orange, tractor, porcupine, girl, skunk, crocodile, dolphin, lamp, train, apple, lawn_mower, bee, mushroom, spider, bus, otter, boy, castle, rose, road, snail, cattle, wolf, tulip, cloud, streetcar, worm, telephone, possum, elephant, motorcycle, beetle, hamster, pickup_truck, rabbit, mountain