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_0734)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 734 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9677 |
| Val Accuracy | 0.8736 |
| Test Accuracy | 0.8674 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, wardrobe, bicycle, dinosaur, hamster, turtle, chair, house, willow_tree, mushroom, snail, cup, streetcar, plain, keyboard, beetle, whale, cockroach, boy, fox, possum, bee, mouse, castle, table, snake, skunk, kangaroo, chimpanzee, shark, aquarium_fish, pickup_truck, beaver, squirrel, caterpillar, pine_tree, palm_tree, camel, cattle, bridge, apple, raccoon, girl, orchid, road, clock, ray, wolf, forest, mountain