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_0956)
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 | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 956 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9884 |
| Val Accuracy | 0.8936 |
| Test Accuracy | 0.8844 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, maple_tree, can, tractor, caterpillar, rose, castle, rabbit, oak_tree, seal, bottle, cockroach, butterfly, bridge, skyscraper, mushroom, bowl, wolf, orchid, tulip, worm, streetcar, skunk, leopard, trout, shark, pickup_truck, clock, possum, bear, snake, dinosaur, porcupine, crocodile, otter, willow_tree, kangaroo, train, pine_tree, road, lizard, man, squirrel, crab, woman, fox, beaver, raccoon, lion, rocket