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_0153)
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 | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 153 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.2882 |
| Val Accuracy | 0.2672 |
| Test Accuracy | 0.2762 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
ray, television, skyscraper, porcupine, pickup_truck, lizard, snake, skunk, whale, aquarium_fish, flatfish, dolphin, beaver, spider, rabbit, bee, possum, pine_tree, bridge, plain, streetcar, wolf, worm, butterfly, bed, willow_tree, mushroom, bowl, tulip, can, telephone, motorcycle, hamster, poppy, lawn_mower, tractor, caterpillar, bear, leopard, baby, squirrel, rose, house, fox, chair, boy, cockroach, forest, sea, woman