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_0623)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 623 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9982 |
| Val Accuracy | 0.9120 |
| Test Accuracy | 0.9112 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, plain, aquarium_fish, chimpanzee, tractor, can, train, lobster, camel, tulip, castle, cockroach, girl, beetle, bottle, sweet_pepper, palm_tree, rabbit, telephone, turtle, mouse, willow_tree, boy, cattle, dolphin, possum, bicycle, chair, orange, caterpillar, shark, woman, plate, keyboard, worm, road, ray, rose, whale, seal, wolf, tank, streetcar, squirrel, elephant, wardrobe, cloud, oak_tree, bridge, mountain