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_0621)
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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 621 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9277 |
| Test Accuracy | 0.9316 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, bowl, road, can, pine_tree, girl, streetcar, orange, wardrobe, plate, skyscraper, beetle, caterpillar, cockroach, lobster, dolphin, motorcycle, sweet_pepper, squirrel, hamster, plain, butterfly, palm_tree, shark, raccoon, spider, turtle, possum, table, porcupine, tank, otter, tulip, lawn_mower, beaver, apple, poppy, wolf, couch, bicycle, keyboard, chimpanzee, camel, mouse, television, cattle, woman, mountain, elephant, trout