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_0943)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 943 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.9155 |
| Test Accuracy | 0.9200 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, bottle, butterfly, leopard, willow_tree, crocodile, rocket, otter, road, shrew, elephant, train, man, worm, maple_tree, oak_tree, aquarium_fish, mushroom, caterpillar, turtle, camel, bicycle, wolf, bed, snail, skyscraper, bee, orchid, castle, girl, mountain, poppy, plate, forest, dinosaur, bus, lobster, orange, snake, woman, mouse, wardrobe, porcupine, keyboard, whale, sea, hamster, kangaroo, cattle, table