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_0588)
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 | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 588 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4071 |
| Val Accuracy | 0.3723 |
| Test Accuracy | 0.3674 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, seal, snail, sea, crab, fox, lamp, hamster, sunflower, pear, train, oak_tree, shrew, streetcar, willow_tree, snake, cup, cattle, rocket, bed, mouse, skyscraper, tractor, orange, sweet_pepper, bottle, mountain, tank, couch, skunk, forest, camel, plate, cloud, elephant, flatfish, chimpanzee, tulip, bicycle, pickup_truck, crocodile, rabbit, aquarium_fish, plain, telephone, chair, leopard, dinosaur, otter, worm