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_0017)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 17 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9865 |
| Val Accuracy | 0.9032 |
| Test Accuracy | 0.8980 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, oak_tree, cockroach, skunk, lizard, kangaroo, seal, possum, lion, leopard, crocodile, butterfly, television, rocket, bicycle, otter, dolphin, woman, mushroom, pear, lawn_mower, poppy, aquarium_fish, sea, raccoon, tractor, rabbit, telephone, keyboard, house, rose, lamp, orange, lobster, plain, train, pickup_truck, skyscraper, maple_tree, sunflower, whale, can, mouse, couch, snake, castle, man, plate, tulip, snail