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_0885)
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 |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 885 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9757 |
| Val Accuracy | 0.8496 |
| Test Accuracy | 0.8450 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, keyboard, boy, pear, skunk, bicycle, orange, apple, pine_tree, forest, television, streetcar, skyscraper, bee, shark, mushroom, tulip, sweet_pepper, baby, pickup_truck, cockroach, rocket, turtle, rose, poppy, clock, aquarium_fish, oak_tree, whale, shrew, cattle, lawn_mower, woman, possum, table, mouse, cloud, road, bus, spider, sunflower, lobster, tank, sea, maple_tree, orchid, cup, rabbit, couch, dinosaur