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_0006)
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_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 6 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9189 |
| Test Accuracy | 0.9240 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, snake, lion, fox, television, clock, willow_tree, porcupine, forest, beaver, streetcar, beetle, trout, rose, boy, cup, train, cattle, rabbit, plain, apple, sunflower, skunk, girl, elephant, chair, worm, otter, bicycle, tulip, sea, cockroach, orange, bottle, crocodile, chimpanzee, bowl, tank, ray, orchid, wardrobe, road, keyboard, dolphin, lizard, squirrel, castle, rocket, bee, poppy