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_0550)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 550 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.9267 |
| Test Accuracy | 0.9244 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
forest, baby, poppy, aquarium_fish, bicycle, couch, willow_tree, table, pine_tree, worm, mushroom, telephone, chimpanzee, boy, chair, train, skunk, mountain, beetle, shrew, plain, sweet_pepper, lizard, crocodile, pear, camel, fox, dolphin, flatfish, rabbit, castle, lawn_mower, oak_tree, trout, cockroach, lamp, possum, keyboard, ray, rocket, cattle, otter, house, hamster, seal, bowl, pickup_truck, kangaroo, sunflower, orchid