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_0205)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 205 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2784 |
| Val Accuracy | 0.2749 |
| Test Accuracy | 0.2634 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, woman, cloud, orchid, possum, cattle, ray, sunflower, squirrel, caterpillar, oak_tree, wardrobe, butterfly, dinosaur, crab, crocodile, girl, pine_tree, rose, plain, keyboard, snail, pickup_truck, mountain, shrew, lizard, motorcycle, table, raccoon, tiger, rabbit, trout, aquarium_fish, man, boy, bottle, bed, couch, pear, television, baby, porcupine, bicycle, house, palm_tree, cockroach, tractor, road, bear, maple_tree