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_0093)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 93 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9139 |
| Test Accuracy | 0.9166 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lobster, rabbit, rocket, bed, house, snake, motorcycle, tulip, mouse, dolphin, boy, dinosaur, man, spider, can, caterpillar, mountain, telephone, pear, road, crab, keyboard, trout, bridge, bottle, wolf, cup, couch, woman, rose, lion, aquarium_fish, tank, willow_tree, crocodile, table, tractor, raccoon, skunk, flatfish, castle, bicycle, chimpanzee, cattle, butterfly, chair, shrew, plain, pine_tree, turtle