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_0918)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 918 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9765 |
| Val Accuracy | 0.8893 |
| Test Accuracy | 0.8900 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, spider, sea, elephant, bicycle, crocodile, kangaroo, plate, shrew, lion, lawn_mower, oak_tree, hamster, crab, girl, leopard, skunk, dolphin, couch, sunflower, cup, dinosaur, mountain, telephone, forest, table, train, tiger, can, boy, rabbit, flatfish, cattle, bed, chimpanzee, castle, rocket, tulip, television, tractor, pine_tree, possum, caterpillar, bowl, shark, worm, turtle, skyscraper, bottle, bear