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_0948)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 948 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7205 |
| Val Accuracy | 0.4515 |
| Test Accuracy | 0.4460 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, sunflower, cattle, clock, lawn_mower, bee, possum, shark, road, bus, bottle, pickup_truck, oak_tree, streetcar, fox, bowl, sweet_pepper, mountain, tiger, pine_tree, chimpanzee, plate, girl, rose, orchid, bicycle, mouse, sea, crocodile, worm, lobster, train, keyboard, cloud, porcupine, lamp, forest, ray, hamster, beetle, palm_tree, spider, lion, baby, chair, raccoon, lizard, otter, rabbit, motorcycle