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_0306)
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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 306 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9232 |
| Test Accuracy | 0.9278 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
caterpillar, skyscraper, forest, cup, house, bee, worm, cockroach, pickup_truck, seal, shrew, aquarium_fish, plain, willow_tree, dolphin, mountain, fox, plate, sweet_pepper, bed, cloud, chair, porcupine, turtle, bridge, table, telephone, ray, tiger, poppy, whale, tulip, rose, bear, bottle, crab, beetle, lawn_mower, road, hamster, snake, leopard, train, spider, butterfly, snail, couch, lizard, man, can