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_0256)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 256 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9173 |
| Test Accuracy | 0.9230 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, kangaroo, beetle, streetcar, plain, butterfly, keyboard, chimpanzee, boy, castle, apple, cloud, mushroom, crocodile, aquarium_fish, orchid, bicycle, bus, baby, camel, motorcycle, shark, chair, elephant, road, can, plate, beaver, raccoon, turtle, lion, pickup_truck, shrew, bridge, maple_tree, sunflower, dinosaur, seal, bowl, bee, mouse, bed, hamster, lobster, tractor, worm, crab, willow_tree, pine_tree, otter