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_0149)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 149 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9240 |
| Test Accuracy | 0.9166 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, wardrobe, tank, whale, train, sea, ray, rocket, shrew, rose, bus, orange, bridge, couch, bowl, worm, girl, pear, baby, telephone, mountain, camel, can, road, streetcar, flatfish, wolf, porcupine, beetle, cloud, plain, cattle, spider, hamster, possum, keyboard, pickup_truck, orchid, elephant, caterpillar, sunflower, lizard, palm_tree, dolphin, tiger, television, aquarium_fish, otter, apple, clock