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_0979)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 979 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3290 |
| Val Accuracy | 0.3245 |
| Test Accuracy | 0.3166 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, otter, bear, fox, chimpanzee, lobster, maple_tree, beetle, mouse, clock, cockroach, worm, forest, tiger, mountain, bridge, aquarium_fish, orange, tractor, shark, orchid, lion, train, keyboard, plate, cloud, snail, wardrobe, plain, seal, pear, ray, can, road, bicycle, rose, woman, wolf, lawn_mower, bus, sunflower, crocodile, palm_tree, willow_tree, chair, caterpillar, motorcycle, squirrel, rabbit, whale