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_0691)
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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 691 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9200 |
| Test Accuracy | 0.9212 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, keyboard, girl, lobster, sea, flatfish, shrew, bear, house, skunk, dinosaur, squirrel, trout, spider, apple, television, poppy, plain, hamster, mouse, baby, beetle, beaver, tractor, elephant, castle, raccoon, clock, cloud, leopard, sweet_pepper, fox, cattle, bowl, forest, train, crab, snake, lion, couch, cup, bicycle, butterfly, tank, orange, bee, tiger, seal, pickup_truck, maple_tree