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_0278)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 278 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9937 |
| Val Accuracy | 0.9232 |
| Test Accuracy | 0.9172 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
road, whale, oak_tree, palm_tree, mountain, chimpanzee, butterfly, clock, hamster, streetcar, crocodile, snake, skunk, train, table, wolf, pine_tree, aquarium_fish, bee, porcupine, spider, keyboard, elephant, wardrobe, tank, trout, tiger, shark, woman, snail, crab, can, sunflower, rabbit, beaver, mouse, maple_tree, lawn_mower, sea, baby, flatfish, couch, raccoon, squirrel, motorcycle, rose, fox, rocket, house, tractor