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_0632)
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 | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 632 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9995 |
| Val Accuracy | 0.9211 |
| Test Accuracy | 0.9264 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, rabbit, mouse, cockroach, spider, dolphin, possum, cattle, forest, road, streetcar, whale, plate, otter, lion, bottle, skyscraper, can, snake, man, boy, castle, raccoon, orchid, lamp, wolf, rocket, dinosaur, bridge, crocodile, keyboard, palm_tree, television, mountain, leopard, woman, bee, telephone, worm, poppy, pickup_truck, plain, train, ray, bowl, hamster, lobster, turtle, caterpillar, sea