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_0401)
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 | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 401 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9740 |
| Val Accuracy | 0.8587 |
| Test Accuracy | 0.8452 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
poppy, maple_tree, bowl, woman, rose, orange, fox, chimpanzee, bus, apple, lawn_mower, whale, road, bicycle, cloud, castle, tulip, bed, trout, chair, palm_tree, flatfish, lion, dolphin, mouse, cup, table, leopard, man, forest, turtle, lamp, pear, lobster, tiger, skyscraper, ray, telephone, girl, snail, worm, beetle, sweet_pepper, crab, cattle, rabbit, cockroach, can, porcupine, elephant