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_0641)
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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 641 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9984 |
| Val Accuracy | 0.9099 |
| Test Accuracy | 0.9162 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
apple, porcupine, lobster, caterpillar, boy, shrew, girl, cockroach, bicycle, television, couch, house, bowl, road, fox, sea, bus, raccoon, snail, dinosaur, sweet_pepper, tractor, woman, motorcycle, possum, cup, worm, orchid, maple_tree, flatfish, lion, mountain, crocodile, sunflower, cattle, spider, train, streetcar, palm_tree, snake, skunk, man, bridge, baby, bear, pickup_truck, kangaroo, dolphin, rabbit, ray