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_0741)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 741 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9365 |
| Test Accuracy | 0.9360 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orange, cloud, cockroach, motorcycle, flatfish, maple_tree, beaver, boy, man, woman, lawn_mower, crocodile, lamp, chair, apple, lobster, orchid, camel, aquarium_fish, bottle, spider, dinosaur, plate, sunflower, rocket, tractor, tank, sweet_pepper, house, trout, raccoon, pear, elephant, telephone, bicycle, table, willow_tree, streetcar, crab, snake, bed, whale, sea, bridge, forest, beetle, butterfly, castle, bee, keyboard