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_0135)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 135 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9240 |
| Test Accuracy | 0.9128 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, rose, rocket, kangaroo, castle, house, baby, oak_tree, snake, shrew, forest, cockroach, plain, spider, shark, crocodile, cup, beaver, girl, streetcar, lobster, flatfish, snail, raccoon, telephone, chair, cattle, tulip, tank, fox, hamster, woman, lamp, butterfly, keyboard, turtle, orchid, motorcycle, porcupine, bicycle, squirrel, mushroom, tiger, table, willow_tree, possum, mountain, trout, dolphin, seal