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_0416)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 416 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5812 |
| Val Accuracy | 0.4141 |
| Test Accuracy | 0.4330 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
table, woman, keyboard, can, crab, cup, sunflower, skyscraper, skunk, orchid, shrew, boy, turtle, whale, flatfish, mouse, bee, couch, bottle, snail, telephone, rose, bowl, lizard, chair, lobster, kangaroo, apple, lion, seal, television, caterpillar, oak_tree, elephant, plain, tractor, willow_tree, mountain, man, fox, forest, bus, cloud, cockroach, pickup_truck, spider, worm, train, dinosaur, pear