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_0014)
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 | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 14 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5416 |
| Val Accuracy | 0.4107 |
| Test Accuracy | 0.4178 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, baby, pickup_truck, cup, house, sunflower, cockroach, squirrel, mountain, willow_tree, castle, dolphin, bottle, worm, shark, motorcycle, oak_tree, couch, bed, mouse, table, cattle, possum, fox, pine_tree, wardrobe, snail, clock, can, dinosaur, porcupine, plate, bicycle, skyscraper, tractor, bus, crab, train, butterfly, shrew, chair, pear, camel, elephant, bear, girl, crocodile, road, trout, rabbit