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_0958)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 958 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9235 |
| Test Accuracy | 0.9246 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, caterpillar, cup, television, squirrel, apple, rose, girl, snake, road, dinosaur, pear, couch, crocodile, elephant, orange, clock, cattle, lizard, man, spider, leopard, dolphin, woman, bicycle, pine_tree, rabbit, can, whale, train, bridge, seal, flatfish, worm, trout, baby, tiger, sunflower, shrew, snail, turtle, tulip, hamster, motorcycle, lobster, lamp, bear, table, plain, camel