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_0548)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 548 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9857 |
| Val Accuracy | 0.9093 |
| Test Accuracy | 0.9194 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, plate, castle, house, pickup_truck, chimpanzee, bed, boy, aquarium_fish, girl, wolf, clock, pear, rose, rocket, fox, road, rabbit, plain, raccoon, motorcycle, palm_tree, lizard, turtle, poppy, cup, tractor, bus, oak_tree, bowl, butterfly, tank, bee, orchid, cockroach, lion, bicycle, cloud, porcupine, wardrobe, cattle, hamster, skunk, chair, beetle, table, sweet_pepper, pine_tree, worm, apple