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_0249)
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 | test |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 249 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9935 |
| Val Accuracy | 0.9011 |
| Test Accuracy | 0.8936 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
leopard, pickup_truck, chimpanzee, rose, possum, motorcycle, rocket, house, aquarium_fish, wardrobe, tulip, sea, girl, skyscraper, shrew, bed, lamp, worm, bear, dinosaur, crab, orange, flatfish, woman, otter, hamster, cloud, pear, beaver, camel, baby, palm_tree, willow_tree, bicycle, tiger, bee, snail, porcupine, road, plate, castle, mountain, bottle, maple_tree, forest, sweet_pepper, fox, couch, seal, orchid