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_0980)
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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 980 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9981 |
| Val Accuracy | 0.9101 |
| Test Accuracy | 0.9084 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lamp, cloud, forest, train, raccoon, butterfly, chimpanzee, beaver, turtle, road, seal, cattle, bee, rose, otter, shark, keyboard, house, elephant, television, willow_tree, kangaroo, possum, can, snake, chair, apple, table, bottle, tractor, bear, mouse, telephone, camel, fox, orange, rocket, lobster, wardrobe, crocodile, bowl, maple_tree, cup, poppy, crab, clock, pine_tree, flatfish, dolphin, shrew