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_0988)
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 | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 988 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9133 |
| Test Accuracy | 0.9136 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lamp, plain, woman, turtle, cattle, butterfly, can, lawn_mower, castle, tiger, oak_tree, pear, sweet_pepper, bee, caterpillar, fox, lizard, possum, clock, whale, bear, boy, keyboard, beetle, rose, streetcar, girl, elephant, telephone, trout, bus, squirrel, rocket, pine_tree, crab, hamster, cockroach, maple_tree, cup, skunk, apple, television, shark, kangaroo, cloud, man, lobster, bed, pickup_truck, train