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_0395)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 395 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9708 |
| Val Accuracy | 0.8723 |
| Test Accuracy | 0.8734 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, mountain, train, oak_tree, bicycle, bed, butterfly, fox, maple_tree, television, cattle, rose, can, bowl, mushroom, shrew, wardrobe, lobster, streetcar, flatfish, elephant, plate, bottle, tank, sweet_pepper, woman, girl, ray, crocodile, seal, shark, raccoon, pear, road, bus, willow_tree, chimpanzee, aquarium_fish, dolphin, forest, clock, tulip, chair, wolf, rocket, lamp, lizard, spider, orange, tractor