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_0483)
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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 483 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4120 |
| Val Accuracy | 0.3909 |
| Test Accuracy | 0.3828 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, sea, lion, squirrel, spider, tank, orange, bear, trout, lamp, cattle, hamster, train, keyboard, bridge, poppy, beetle, rose, snail, worm, shrew, possum, mountain, ray, maple_tree, porcupine, bicycle, television, bowl, plain, elephant, motorcycle, crab, pickup_truck, palm_tree, bus, orchid, lobster, dinosaur, plate, table, skyscraper, wolf, cockroach, couch, chair, telephone, pear, tiger, apple