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_0155)
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 | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 155 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9750 |
| Val Accuracy | 0.8651 |
| Test Accuracy | 0.8566 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, ray, cloud, spider, plate, chair, bear, mushroom, sea, maple_tree, bus, keyboard, possum, bicycle, aquarium_fish, wolf, bottle, chimpanzee, rocket, crocodile, whale, porcupine, girl, motorcycle, tiger, leopard, bed, lizard, skunk, bee, woman, elephant, baby, orange, turtle, pear, beaver, cockroach, snail, road, apple, telephone, couch, pine_tree, wardrobe, mouse, poppy, orchid, beetle, worm