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_0781)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 781 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4857 |
| Val Accuracy | 0.3925 |
| Test Accuracy | 0.4032 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beetle, dinosaur, seal, whale, wardrobe, forest, rose, mountain, tank, raccoon, willow_tree, rocket, baby, aquarium_fish, poppy, snake, mushroom, oak_tree, kangaroo, elephant, keyboard, train, cockroach, crab, castle, crocodile, cup, boy, bus, streetcar, possum, fox, road, tulip, lamp, mouse, ray, spider, plate, lion, chimpanzee, squirrel, sunflower, bed, caterpillar, skunk, can, lawn_mower, hamster, wolf