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_0791)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 791 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5746 |
| Val Accuracy | 0.4597 |
| Test Accuracy | 0.4734 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, clock, lion, tractor, snake, bridge, kangaroo, girl, wolf, porcupine, elephant, bicycle, butterfly, oak_tree, palm_tree, camel, television, table, beaver, cup, chair, shark, dinosaur, snail, plate, can, bee, leopard, rabbit, wardrobe, mountain, sunflower, lobster, forest, man, skunk, skyscraper, aquarium_fish, cloud, bus, tulip, lamp, whale, flatfish, sweet_pepper, poppy, bear, orchid, castle, road