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_0972)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 972 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3952 |
| Val Accuracy | 0.3723 |
| Test Accuracy | 0.3624 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, forest, lamp, tank, pine_tree, sunflower, raccoon, snail, camel, leopard, shrew, telephone, squirrel, wardrobe, seal, tiger, lawn_mower, fox, bottle, rabbit, beetle, man, skunk, flatfish, television, mountain, chimpanzee, bear, table, cattle, skyscraper, chair, tulip, dinosaur, plain, cup, caterpillar, oak_tree, house, couch, elephant, snake, willow_tree, bee, keyboard, whale, poppy, cockroach, turtle, hamster