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_0750)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 750 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9744 |
| Val Accuracy | 0.8461 |
| Test Accuracy | 0.8416 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lizard, pine_tree, oak_tree, bee, rose, road, can, kangaroo, lamp, cup, apple, seal, snail, fox, bear, dinosaur, skyscraper, telephone, girl, mushroom, snake, rocket, rabbit, otter, house, crocodile, bowl, sunflower, hamster, bottle, mouse, man, table, butterfly, aquarium_fish, sweet_pepper, pear, shark, squirrel, possum, leopard, cattle, mountain, worm, poppy, camel, whale, television, dolphin, wardrobe