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_0106)
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_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 106 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9712 |
| Val Accuracy | 0.8928 |
| Test Accuracy | 0.8924 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
road, house, orange, girl, leopard, flatfish, maple_tree, apple, pear, caterpillar, couch, streetcar, turtle, hamster, mushroom, tank, raccoon, woman, crocodile, rabbit, wolf, snake, forest, camel, chimpanzee, television, boy, shrew, skyscraper, elephant, cockroach, fox, willow_tree, bed, sunflower, orchid, porcupine, plain, otter, lamp, snail, aquarium_fish, pine_tree, lizard, trout, squirrel, skunk, sweet_pepper, dinosaur, palm_tree