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_0900)
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 | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 900 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9418 |
| Val Accuracy | 0.8336 |
| Test Accuracy | 0.8334 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
aquarium_fish, shrew, road, snail, dinosaur, bee, clock, couch, possum, wolf, raccoon, tiger, chimpanzee, skyscraper, caterpillar, girl, worm, butterfly, maple_tree, can, train, pine_tree, wardrobe, tank, mouse, flatfish, orchid, cattle, bicycle, castle, turtle, plain, squirrel, poppy, hamster, mountain, rabbit, boy, beaver, cloud, bed, bear, seal, bridge, baby, tulip, lizard, sweet_pepper, crab, otter