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_0696)
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 | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 696 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9976 |
| Val Accuracy | 0.9029 |
| Test Accuracy | 0.9100 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, orange, shark, beaver, trout, worm, lobster, crab, wolf, couch, possum, bowl, raccoon, sweet_pepper, plate, streetcar, aquarium_fish, sea, apple, pine_tree, sunflower, otter, oak_tree, cockroach, shrew, snake, leopard, rocket, seal, forest, elephant, lawn_mower, tractor, bear, mouse, pear, mountain, skyscraper, motorcycle, hamster, whale, bed, table, train, woman, crocodile, maple_tree, fox, baby, plain