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_0484)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 484 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9763 |
| Val Accuracy | 0.8523 |
| Test Accuracy | 0.8482 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, fox, telephone, trout, snail, tractor, lobster, lion, cup, bed, caterpillar, beetle, pickup_truck, chimpanzee, elephant, rose, poppy, motorcycle, shark, bear, worm, camel, snake, dinosaur, orange, hamster, boy, chair, mouse, house, lawn_mower, clock, leopard, shrew, aquarium_fish, seal, mountain, sweet_pepper, pear, spider, willow_tree, crocodile, ray, bee, lamp, orchid, tank, raccoon, cattle, couch