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_0250)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 250 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9558 |
| Val Accuracy | 0.8443 |
| Test Accuracy | 0.8402 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, bicycle, aquarium_fish, elephant, mouse, girl, bed, cloud, camel, otter, raccoon, hamster, shark, plain, tiger, turtle, wardrobe, spider, chimpanzee, cockroach, lobster, road, porcupine, clock, poppy, cup, mushroom, couch, orchid, forest, mountain, sea, castle, bear, bus, lamp, plate, skyscraper, keyboard, trout, tank, train, worm, table, lizard, caterpillar, beetle, man, rose, squirrel