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_0071)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 71 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9781 |
| Val Accuracy | 0.8664 |
| Test Accuracy | 0.8692 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, orchid, possum, hamster, television, shrew, skunk, boy, elephant, tulip, road, plain, keyboard, squirrel, man, dinosaur, apple, spider, aquarium_fish, cloud, bus, butterfly, whale, bed, flatfish, clock, castle, bee, palm_tree, lawn_mower, sunflower, caterpillar, lobster, orange, rocket, poppy, beetle, seal, woman, shark, can, house, bowl, forest, mountain, bridge, leopard, lizard, camel, cattle