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_0366)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 366 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9534 |
| Val Accuracy | 0.8571 |
| Test Accuracy | 0.8376 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, motorcycle, lion, bee, lobster, fox, caterpillar, bowl, woman, table, shark, whale, chimpanzee, skyscraper, couch, bus, apple, house, orchid, trout, sea, dinosaur, mountain, can, streetcar, skunk, telephone, cloud, girl, television, mushroom, rabbit, oak_tree, beetle, keyboard, poppy, train, clock, willow_tree, leopard, tractor, wolf, sweet_pepper, kangaroo, plate, porcupine, snake, pine_tree, lamp, plain