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_0795)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 795 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9684 |
| Val Accuracy | 0.8797 |
| Test Accuracy | 0.8674 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bus, telephone, girl, streetcar, clock, cloud, snake, beetle, worm, shrew, camel, cattle, lobster, tiger, bee, hamster, table, mushroom, motorcycle, pear, lamp, possum, cockroach, dinosaur, squirrel, lion, dolphin, train, snail, crab, oak_tree, shark, bicycle, skyscraper, keyboard, willow_tree, chimpanzee, sweet_pepper, pickup_truck, trout, turtle, wardrobe, elephant, cup, tractor, orange, couch, bed, butterfly, sunflower