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_0456)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 456 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9216 |
| Test Accuracy | 0.9152 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, possum, lizard, pickup_truck, tractor, dinosaur, beaver, willow_tree, forest, baby, girl, table, elephant, tiger, wolf, poppy, kangaroo, skyscraper, porcupine, flatfish, palm_tree, house, crocodile, snail, woman, chair, orchid, ray, plain, bowl, plate, trout, snake, cattle, cockroach, bottle, oak_tree, fox, orange, lamp, bed, man, seal, skunk, road, bear, cup, camel, aquarium_fish, otter