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_0831)
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 | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 831 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2357 |
| Val Accuracy | 0.2309 |
| Test Accuracy | 0.2284 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, hamster, tank, keyboard, rose, squirrel, telephone, crab, orange, poppy, bus, camel, tractor, pine_tree, seal, boy, beaver, wolf, willow_tree, elephant, girl, forest, trout, kangaroo, leopard, lion, skyscraper, raccoon, cockroach, rabbit, caterpillar, castle, cup, can, bee, lobster, beetle, aquarium_fish, train, lizard, house, possum, orchid, chair, pickup_truck, tulip, butterfly, worm, apple, palm_tree