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_0391)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 391 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4588 |
| Val Accuracy | 0.3877 |
| Test Accuracy | 0.3822 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, worm, poppy, table, dinosaur, bottle, willow_tree, tulip, wolf, squirrel, cattle, crocodile, mountain, train, bus, chimpanzee, elephant, mouse, shrew, snail, streetcar, couch, can, maple_tree, crab, lamp, skunk, sea, caterpillar, bear, snake, hamster, possum, pine_tree, turtle, man, bed, chair, bowl, cloud, tractor, woman, lizard, shark, forest, palm_tree, lawn_mower, fox, bridge, oak_tree