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_0126)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 126 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4214 |
| Val Accuracy | 0.3464 |
| Test Accuracy | 0.3646 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, streetcar, couch, seal, rose, beaver, bowl, skyscraper, pine_tree, crocodile, porcupine, beetle, woman, rocket, dolphin, trout, leopard, pear, shrew, lion, hamster, turtle, oak_tree, mouse, lamp, pickup_truck, caterpillar, train, tulip, rabbit, dinosaur, orange, maple_tree, tiger, house, crab, bridge, tractor, bear, chimpanzee, sunflower, chair, cockroach, plate, mushroom, otter, telephone, fox, keyboard, worm