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_0002)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 2 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2574 |
| Val Accuracy | 0.2376 |
| Test Accuracy | 0.2394 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, aquarium_fish, lawn_mower, lizard, clock, otter, squirrel, cattle, couch, bear, crab, pear, bed, chair, turtle, shark, tank, possum, shrew, motorcycle, mushroom, kangaroo, beaver, plain, man, lamp, streetcar, lion, table, train, crocodile, snake, keyboard, rabbit, worm, spider, fox, telephone, mouse, hamster, forest, chimpanzee, rocket, girl, road, ray, tiger, bee, flatfish, willow_tree