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_0971)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 971 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9187 |
| Val Accuracy | 0.8440 |
| Test Accuracy | 0.8328 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chimpanzee, porcupine, elephant, man, oak_tree, clock, mouse, rose, caterpillar, lobster, bed, lawn_mower, flatfish, bottle, rocket, maple_tree, mountain, shrew, girl, boy, plain, lion, leopard, wolf, squirrel, tiger, tractor, poppy, kangaroo, snake, raccoon, butterfly, cloud, bridge, couch, spider, sunflower, fox, whale, telephone, camel, skunk, otter, can, beaver, baby, chair, pear, keyboard, road