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_0142)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 142 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9785 |
| Val Accuracy | 0.9005 |
| Test Accuracy | 0.8990 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
can, otter, whale, orange, train, wolf, rocket, beaver, tiger, aquarium_fish, television, turtle, telephone, bicycle, forest, rabbit, camel, lizard, poppy, palm_tree, bee, lawn_mower, orchid, woman, bus, hamster, bed, cloud, kangaroo, man, motorcycle, house, maple_tree, bridge, pine_tree, butterfly, raccoon, shark, bear, trout, fox, clock, snake, girl, caterpillar, tulip, lion, chair, possum, beetle