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_0782)
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 | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 782 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9884 |
| Val Accuracy | 0.8741 |
| Test Accuracy | 0.8730 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beetle, porcupine, tiger, pickup_truck, man, chimpanzee, streetcar, girl, snake, leopard, rabbit, willow_tree, bowl, dinosaur, lobster, flatfish, rocket, plain, skunk, snail, bear, caterpillar, sunflower, forest, poppy, house, dolphin, worm, boy, bee, palm_tree, raccoon, road, bicycle, ray, turtle, tulip, beaver, television, mushroom, shark, pine_tree, hamster, cup, wardrobe, seal, kangaroo, sweet_pepper, squirrel, mouse